© 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. 44039
    Prev
    Next
    INDEX
    Explanations

    lington

    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
    lington
    -1.20
     Refle
    -0.59
    ViewImports
    -0.57
     limitée
    -0.57
    rrggbb
    -0.56
    Mist
    -0.55
    bellum
    -0.54
     cliquant
    -0.54
    εύ
    -0.54
    ніципалі
    -0.53
    POSITIVE LOGITS
    __*/
    0.57
    UTERS
    0.52
    TagMode
    0.50
    MLLoader
    0.50
    cần
    0.49
    OrBuilder
    0.49
    setupUi
    0.48
    catraz
    0.48
    CopyWith
    0.47
    GroupLayout
    0.46
    Activations Density 0.135%

    No Known Activations