© 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. 0-CLT-HP
    4. 1118
    Prev
    Next
    INDEX
    Explanations

    scientific/technical

    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
    Portale
    -0.72
    بوابة
    -0.65
    ISupport
    -0.65
     createSlice
    -0.65
    AnimationsModule
    -0.64
    脚注の使い方
    -0.63
    cavity
    -0.61
     ExecuteAsync
    -0.60
    مصادر
    -0.59
    ArrowToggle
    -0.59
    POSITIVE LOGITS
    ly
    0.75
    tre
    0.63
    ",@"
    0.61
    r
    0.59
    day
    0.55
    don
    0.55
    yy
    0.53
    ders
    0.53
    dar
    0.53
    LY
    0.52
    Activations Density 0.029%

    No Known Activations