© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4802
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical strength and bodybuilding

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    764
    +0.19
    0.7%
    1978
    +0.18
    0.7%
    1224
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1531
    +0.19
    0.08
    764
    +0.18
    0.08
    2044
    +0.13
    0.11
    Negative Logits
     alkoh
    -0.93
     makro
    -0.91
     solidar
    -0.86
     Kategor
    -0.85
     Okt
    -0.84
     lampa
    -0.83
     induk
    -0.83
     fono
    -0.82
     uhr
    -0.82
     teras
    -0.82
    POSITIVE LOGITS
     unspeak
    1.18
     ecru
    1.11
     cushi
    1.09
     unwarran
    1.08
     hairc
    1.06
     disreg
    1.06
     indestru
    1.03
     Shakspeare
    1.02
     swarovski
    1.02
     poetical
    1.02
    Activations Density 1.637%

    No Known Activations