© 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 EvalsExportsAPI 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. 14847
    Prev
    Next
    INDEX
    Explanations

    phrases related to limits and boundaries

    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
    313
    +0.12
    0.4%
    528
    +0.11
    0.4%
    241
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.12
    0.02
    241
    +0.11
    0.02
    1516
    +0.10
    0.02
    Negative Logits
     stoff
    -0.68
     akti
    -0.68
     alkoh
    -0.67
     kram
    -0.66
     kado
    -0.64
     kras
    -0.64
     makro
    -0.62
     kog
    -0.61
     Kategor
    -0.61
     cso
    -0.60
    POSITIVE LOGITS
     limit
    1.18
    limit
    1.14
     limits
    1.13
    Limit
    1.12
     Limit
    1.11
     Limits
    1.05
    LIMIT
    1.01
    limits
    0.99
    Limits
    0.97
     LIMIT
    0.96
    Activations Density 0.056%

    No Known Activations