© 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. 1131
    Prev
    Next
    INDEX
    Explanations

    clear

    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
     clear
    -2.31
    clear
    -2.00
     Clear
    -1.73
     obvious
    -1.69
    Clear
    -1.66
    obvious
    -1.45
     CLEAR
    -1.34
     clearer
    -1.34
     claras
    -1.31
     clearest
    -1.27
    POSITIVE LOGITS
    IntoConstraints
    0.80
    inaison
    0.77
     estekak
    0.76
    LookAnd
    0.76
    MigrationBuilder
    0.76
    izable
    0.68
    PerformLayout
    0.67
    shine
    0.66
     تضيفلها
    0.66
    ableView
    0.65
    Activations Density 0.105%

    No Known Activations