© 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. 439
    Prev
    Next
    INDEX
    Explanations

    perfect

    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
     of
    -0.68
     that
    -0.68
    .
    -0.66
     république
    -0.64
    ValueStyle
    -0.61
    createStatement
    -0.60
     bonté
    -0.60
    ;
    -0.59
     estimés
    -0.59
     as
    -0.59
    POSITIVE LOGITS
     Dux
    0.56
     loophole
    0.54
     WJ
    0.53
     batch
    0.52
     Margo
    0.50
     bres
    0.49
     Mez
    0.49
    IContainer
    0.49
     Conscience
    0.49
     salve
    0.49
    Activations Density 0.005%

    No Known Activations