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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95168
    Prev
    Next
    INDEX
    Explanations

    encouraged

    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
     always
    -1.18
    always
    -1.17
    Always
    -1.14
     selalu
    -1.11
     Always
    -1.11
     siempre
    -1.09
     alltid
    -1.09
     altijd
    -1.04
     תמיד
    -1.03
     sempre
    -1.02
    POSITIVE LOGITS
     ExecuteAsync
    0.83
    elemField
    0.82
     jScrollPane
    0.72
    :✨
    0.71
     nakalista
    0.70
    Derbyniad
    0.69
     AssemblyTitle
    0.69
    ValueStyle
    0.66
    ivably
    0.65
    Erreferentziak
    0.65
    Activations Density 0.062%

    No Known Activations