© 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. 2-RES-MATRYOSHKA-DC
    7. 4345
    Prev
    Next
    INDEX
    Explanations

    sequences of special characters or symbols

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <blockquote>
    -0.55
     către
    -0.53
    сов
    -0.47
    mrow
    -0.46
    onBlur
    -0.46
     Hongrie
    -0.45
    ;#
    -0.44
     partenariat
    -0.44
     barbati
    -0.44
     aukš
    -0.43
    POSITIVE LOGITS
    Hentet
    0.91
    StoryboardSegue
    0.87
    PreInfinity
    0.79
     समीक्षक
    0.77
    جستارهای
    0.76
    "}")
    0.75
    AndEndTag
    0.74
     تانيه
    0.74
    ]<<"
    0.73
    principalColumn
    0.72
    Activations Density 0.723%

    No Known Activations