© 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. 20-CLT-HP
    7. 77215
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act-logits · 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
    findpost
    -0.68
    StructEnd
    -0.67
    SizeF
    -0.65
    LookAnd
    -0.63
    TypedDataSet
    -0.57
    UnknownFields
    -0.54
     चीज़ों
    -0.53
    Varint
    -0.52
    basicConfig
    -0.52
    urlencoded
    -0.51
    POSITIVE LOGITS
     réessayer
    0.53
    GenerationType
    0.53
    etera
    0.46
     acesso
    0.44
    wachsene
    0.44
    بوابة
    0.42
    CLR
    0.42
    ISTICS
    0.42
    ché
    0.42
    mids
    0.42
    Activations Density 0.005%

    No Known Activations