© 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. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1009
    Prev
    Next
    INDEX
    Explanations

    commas in the text

    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.22.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.22.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
     which
    -0.79
    %");
    -0.76
    AndEndTag
    -0.73
    MigrationBuilder
    -0.73
    aarrggbb
    -0.71
    */),
    -0.68
    PreferredItem
    -0.66
    which
    -0.66
    ]";
    -0.65
    %";
    -0.65
    POSITIVE LOGITS
     appunto
    0.82
     unfortunately
    0.72
     fortunately
    0.71
     unlike
    0.68
     thankfully
    0.66
     alas
    0.66
     поми
    0.66
     importantly
    0.65
     parado
    0.65
     ironically
    0.65
    Activations Density 0.501%

    No Known Activations