© 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. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 685
    Prev
    Next
    INDEX
    Explanations

    words that are conjunctions or interjections followed by commas

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.79
    
    -0.71
    脚注の使い方
    -0.68
    XtraReports
    -0.67
    ]<<"
    -0.66
     they
    -0.63
    SequentialGroup
    -0.63
     Wikimedijinoj
    -0.62
     []).
    -0.62
    MessageOf
    -0.61
    POSITIVE LOGITS
     alas
    0.81
     honestly
    0.77
     frankly
    0.77
     since
    0.75
     interestingly
    0.75
     here
    0.73
     unlike
    0.71
     unfortunately
    0.71
     as
    0.71
     let
    0.71
    Activations Density 0.716%

    No Known Activations