Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45015
    Prev
    Next
    INDEX
    Explanations

    no

    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
    no
    -0.95
    NO
    -0.82
    eter
    -0.58
     sex
    -0.56
     decline
    -0.52
    ETER
    -0.51
    jno
    -0.49
    nois
    -0.49
    кипе
    -0.48
     estri
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.81
    ValueStyle
    0.73
    principalTable
    0.69
    AddTagHelper
    0.67
    RTSC
    0.67
     MenuView
    0.64
    DeleteBehavior
    0.63
    InitVars
    0.62
    EndContext
    0.61
     تضيفلها
    0.61
    Activations Density 0.090%

    No Known Activations