© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96026
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
    Term
    -0.42
    SerialPort
    -0.39
    Actions
    -0.38
    stufe
    -0.38
     Santo
    -0.38
    addAction
    -0.38
    のだろうか
    -0.38
    väg
    -0.38
    Фа
    -0.37
    geqslant
    -0.37
    POSITIVE LOGITS
    :✨
    0.96
    oa̍t
    0.89
     بيها
    0.81
    AndEndTag
    0.80
     HasFactory
    0.76
    principalColumn
    0.74
    SequentialGroup
    0.74
    ⓧ
    0.73
     Paglinawan
    0.73
     Taktlose
    0.70
    Activations Density 0.086%

    No Known Activations