© 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. 0-CLT-HP
    7. 93059
    Prev
    Next
    INDEX
    Explanations

    sending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.63
     LUMP
    -0.55
     متعلقه
    -0.49
    DoubleQuotes
    -0.49
     ji
    -0.48
     nghi
    -0.48
    endphp
    -0.47
     Wentworth
    -0.46
    SourceChecksum
    -0.46
    ipto
    -0.46
    POSITIVE LOGITS
    <bos>
    0.65
     mukana
    0.63
    FieldNumber
    0.60
    AccessFile
    0.60
    BagConstraints
    0.58
     prochaines
    0.56
    state
    0.55
    Store
    0.54
    FieldDescriptor
    0.54
    UnknownFields
    0.53
    Activations Density 0.299%

    No Known Activations