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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12988
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or investigations

    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
    406
    +0.13
    0.5%
    1535
    +0.12
    0.4%
    1984
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.13
    0.05
    314
    +0.12
    0.05
    331
    +0.12
    0.06
    Negative Logits
     quegli
    -0.77
     virtù
    -0.70
     autunno
    -0.68
     attesa
    -0.62
     Савезне
    -0.56
    vece
    -0.54
     affitto
    -0.54
     anticipo
    -0.53
     overthrown
    -0.53
     Questi
    -0.52
    POSITIVE LOGITS
     svin
    0.89
     benzin
    0.81
     overla
    0.80
     solidar
    0.76
     glan
    0.76
    getIn
    0.76
     respekt
    0.75
    isIn
    0.75
     malin
    0.74
    IsIn
    0.74
    Activations Density 0.359%

    No Known Activations