© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94521
    Prev
    Next
    INDEX
    Explanations

    Code/technical documents

    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
    LookAnd
    -0.50
     Vector
    -0.48
    __':
    -0.45
    ToAction
    -0.43
    Controllo
    -0.42
    Vector
    -0.41
     Bud
    -0.41
    umuz
    -0.41
    zahl
    -0.40
    Ligações
    -0.40
    POSITIVE LOGITS
    Referencoj
    0.59
     ModelExpression
    0.58
    marginHorizontal
    0.57
    اریخ
    0.56
    setVerticalGroup
    0.56
    Przypisy
    0.54
    DockStyle
    0.53
    BASELINE
    0.53
     ब्रेकडाउन
    0.53
    مصادر
    0.52
    Activations Density 0.001%

    No Known Activations