© 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. 0-CLT-HP
    7. 1165
    Prev
    Next
    INDEX
    Explanations

    Formal writing

    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
     vérit
    -0.64
    tande
    -0.56
     tå
    -0.55
     Pref
    -0.53
    sproz
    -0.52
     rød
    -0.51
    tól
    -0.51
    LOAT
    -0.51
    lishes
    -0.50
     truer
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.84
    AutoScaleMode
    0.72
     kasarigan
    0.70
     BoxFit
    0.68
    存于互联网档案馆
    0.68
    fjspx
    0.68
    原始内容存档于
    0.66
     بتاريخ
    0.60
     ModelExpression
    0.59
    SharedCtor
    0.59
    Activations Density 1.404%

    No Known Activations