© 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. 3-RES-MATRYOSHKA-DC
    7. 1119
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and numerical symbols

    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
    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
    <bos>
    -2.02
     
    -1.29
    '
    -1.25
    ’
    -1.17
    "
    -0.99
    “
    -0.95
    </b>
    -0.94
    )
    -0.90
    [
    -0.90
    ",
    -0.90
    POSITIVE LOGITS
     myſelf
    1.16
     itſelf
    0.99
    fjspx
    0.98
     pleaſure
    0.94
    parsedMessage
    0.91
    ſelf
    0.91
    berdayakan
    0.88
     Efq
    0.85
     purpoſe
    0.85
     photolibrary
    0.84
    Activations Density 18.303%

    No Known Activations