© 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. 12-RES-MATRYOSHKA-DC
    7. 32174
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    SharedCtor
    -0.91
    "]));
    -0.88
    ,:);
    -0.85
    adget
    -0.84
    )");
    -0.75
    )";
    -0.74
     Edelman
    -0.73
    "]]
    -0.72
    })*/
    -0.71
    XmlAccessorType
    -0.71
    POSITIVE LOGITS
     torno
    0.57
    SerializeField
    0.53
    enumi
    0.50
     calendar
    0.50
    енти
    0.49
     alignItems
    0.49
     druž
    0.48
     Lus
    0.48
     CURLOPT
    0.48
     življen
    0.47
    Activations Density 0.003%

    No Known Activations