© 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. 1-CLT-HP
    7. 9221
    Prev
    Next
    INDEX
    Explanations

    descriptive texts

    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
    elab
    -0.60
    .
    -0.57
    a
    -0.57
    y
    -0.56
    ier
    -0.55
     f
    -0.54
    g
    -0.54
     of
    -0.52
     to
    -0.52
    le
    -0.52
    POSITIVE LOGITS
     Meksiku
    0.82
     שוליים
    0.82
    ftagPool
    0.82
     HasFactory
    0.75
    LookAnd
    0.72
     betweenstory
    0.71
    Filmographie
    0.71
     myſelf
    0.70
     itſelf
    0.70
     raiſ
    0.70
    Activations Density 0.013%

    No Known Activations