© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94776
    Prev
    Next
    INDEX
    Explanations

    phone

    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
    rogels
    -0.57
     useHistory
    -0.50
    onan
    -0.50
     rangement
    -0.48
    zler
    -0.46
     hookah
    -0.45
    iligten
    -0.45
    赴
    -0.45
    phone
    -0.45
     SqlConnection
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    0.80
    دانشنامهٔ
    0.73
     ExecuteAsync
    0.69
    ValueStyle
    0.67
    OGND
    0.66
    InjectAttribute
    0.66
    (:,:,
    0.63
    DoubleQuotes
    0.60
    MigrationBuilder
    0.60
    calipsis
    0.58
    Activations Density 0.098%

    No Known Activations