© 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. 29522
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or statutes

    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
     kasarigan
    -0.77
     <=",
    -0.75
    دانشنامهٔ
    -0.70
    出版年
    -0.69
    ]));
    -0.69
    WithIOException
    -0.69
    )];
    -0.68
    Демографія
    -0.66
     विश्वसनीयता
    -0.66
    ")));
    -0.66
    POSITIVE LOGITS
    Jur
    0.56
    Grandpa
    0.54
     juridiques
    0.51
    ftime
    0.49
     JUR
    0.49
    راسیون
    0.49
     grand
    0.45
     giuri
    0.45
    IVOS
    0.44
    jande
    0.44
    Activations Density 0.001%

    No Known Activations