© 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. 72176
    Prev
    Next
    INDEX
    Explanations

    Science, code, commentary

    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
    AutoresizingMask
    -0.75
    MigrationBuilder
    -0.64
     ExecuteAsync
    -0.64
    ]-'
    -0.63
    StructEnd
    -0.62
    مصادر
    -0.61
     utafitiHapana
    -0.60
     ModelExpression
    -0.60
     autorytatywna
    -0.60
     AssemblyCulture
    -0.57
    POSITIVE LOGITS
    sizeof
    0.46
     sizeof
    0.46
     TType
    0.45
    XmlAccessorType
    0.44
    ({_
    0.43
    ])).
    0.40
    __":
    0.40
    כון
    0.40
     defaultstate
    0.40
     ignition
    0.40
    Activations Density 0.010%

    No Known Activations