© 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. 1030
    Prev
    Next
    INDEX
    Explanations

    disregard

    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
     gathering
    -0.82
     Gathering
    -0.81
    gathering
    -0.81
     Collecting
    -0.77
    Collecting
    -0.69
    collecting
    -0.69
     collecting
    -0.69
    Gathering
    -0.65
     afterwards
    -0.63
     contrary
    -0.61
    POSITIVE LOGITS
    off
    0.58
    OFF
    0.56
    Off
    0.52
    MigrationBuilder
    0.51
    msgTypes
    0.50
    nachron
    0.49
    PhysRev
    0.49
     kasarigan
    0.48
    pexpr
    0.48
     nhat
    0.47
    Activations Density 1.754%

    No Known Activations