© 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. 94952
    Prev
    Next
    INDEX
    Explanations

    Unicode

    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
    verages
    -0.73
     EClass
    -0.71
    aneous
    -0.66
     resourceCulture
    -0.65
    ateur
    -0.63
    verage
    -0.63
    atory
    -0.59
    migrationBuilder
    -0.59
     للمعارف
    -0.59
    NTIS
    -0.59
    POSITIVE LOGITS
    s
    0.77
    sound
    0.57
    days
    0.56
    day
    0.56
    sport
    0.53
    d
    0.52
    sync
    0.52
    sad
    0.52
    ly
    0.51
    sun
    0.51
    Activations Density 1.627%

    No Known Activations