© 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. 92141
    Prev
    Next
    INDEX
    Explanations

    model

    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
    Autoritní
    -0.82
    principalColumn
    -0.74
    ArgsConstructor
    -0.68
    AsUp
    -0.65
    InjectAttribute
    -0.65
    IUrlHelper
    -0.65
    ChildScrollView
    -0.64
    InvalidProtocol
    -0.63
    Становништво
    -0.60
     виправивши
    -0.59
    POSITIVE LOGITS
     of
    0.68
    kenalkan
    0.52
     zosta
    0.50
    ťou
    0.50
    ReusableCell
    0.50
    曖昧さ回避
    0.49
    ┐
    0.49
     example
    0.47
     village
    0.47
     grandson
    0.45
    Activations Density 0.012%

    No Known Activations