© 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. 1-CLT-HP
    7. 45680
    Prev
    Next
    INDEX
    Explanations

    whose

    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
     发表于
    -0.54
     NSCoder
    -0.54
    UIButton
    -0.53
    EndContext
    -0.51
    //
    -0.50
    IBAction
    -0.50
    脚注の使い方
    -0.46
    akim
    -0.44
    rát
    -0.43
    tedy
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.75
    strix
    0.57
     synthèse
    0.56
     >=",
    0.54
     conva
    0.54
     transverse
    0.53
    usermodel
    0.53
     lengthwise
    0.52
     gravi
    0.52
    doria
    0.52
    Activations Density 0.184%

    No Known Activations