© 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. 45308
    Prev
    Next
    INDEX
    Explanations

    here

    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
    here
    -0.87
    qua
    -0.70
    HERE
    -0.68
    jsxFileName
    -0.57
    i
    -0.57
    irin
    -0.56
    ỉnh
    -0.56
    tede
    -0.54
     csrf
    -0.51
     BIN
    -0.51
    POSITIVE LOGITS
    ChildScrollView
    0.51
    WebElementEntity
    0.50
    glieder
    0.50
    msgTypes
    0.48
    }</
    0.47
    دانشنامهٔ
    0.47
    ihnachts
    0.45
    psack
    0.45
     AllMovie
    0.44
     recensement
    0.44
    Activations Density 0.351%

    No Known Activations