© 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. 1-CLT-HP
    7. 12997
    Prev
    Next
    INDEX
    Explanations

    conflict

    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
    __*/
    -0.57
     remplacé
    -0.57
     disponibilités
    -0.56
    AlterField
    -0.54
    /*
    -0.54
    #
    -0.54
    migrationBuilder
    -0.53
    GOTREF
    -0.53
    awakeFromNib
    -0.51
    MemoryWarning
    -0.50
    POSITIVE LOGITS
    drawImage
    0.54
    grees
    0.52
     Athenian
    0.50
     Seiz
    0.50
    agami
    0.50
    Caps
    0.49
     createState
    0.48
     Calais
    0.48
    ogonal
    0.48
    참고
    0.48
    Activations Density 0.017%

    No Known Activations