© 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. 90921
    Prev
    Next
    INDEX
    Explanations

    characterized

    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
     characterized
    -0.99
    character
    -0.91
    ReusableCell
    -0.85
     characterised
    -0.70
     caractéris
    -0.67
     Polri
    -0.65
     rând
    -0.63
    mapStateToProps
    -0.60
     gawas
    -0.59
    UVWXYZ
    -0.59
    POSITIVE LOGITS
     Chwiliwch
    0.78
     dipl
    0.56
    tif
    0.54
    IUrlHelper
    0.54
    MigrationBuilder
    0.52
    gery
    0.47
    cun
    0.47
    iz
    0.47
    annot
    0.46
    ac
    0.46
    Activations Density 0.114%

    No Known Activations