© 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. 10617
    Prev
    Next
    INDEX
    Explanations

    negative emotions and physical discomfort

    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
    1013
    +0.24
    0.7%
    184
    +0.14
    0.4%
    2034
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.24
    0.11
    284
    +0.14
    0.10
    2044
    +0.10
    0.09
    Negative Logits
     voleva
    -1.04
     dimenti
    -1.04
     stava
    -0.93
     apparti
    -0.93
     faceva
    -0.92
     lancia
    -0.87
     trover
    -0.87
     lavora
    -0.86
     interessa
    -0.86
     dichi
    -0.83
    POSITIVE LOGITS
     unwarran
    0.92
     Shakspeare
    0.90
     McLaugh
    0.90
     but
    0.82
     pamph
    0.75
     snoopy
    0.75
     inappro
    0.75
     disagre
    0.73
     maneu
    0.73
     cuck
    0.72
    Activations Density 0.837%

    No Known Activations