© 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. 5-CLT-HP
    7. 4685
    Prev
    Next
    INDEX
    Explanations

    l

    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
    ed
    -0.88
    y
    -0.79
    s
    -0.69
    i
    -0.69
    a
    -0.68
    ه
    -0.66
    d
    -0.65
    e
    -0.65
    kloped
    -0.65
    t
    -0.63
    POSITIVE LOGITS
     كومونز
    0.77
    IntoConstraints
    0.64
     للمعارف
    0.62
     prêtres
    0.59
    CloseOperation
    0.56
     automatiques
    0.54
    aarrggbb
    0.53
     graphiques
    0.52
     élas
    0.51
    DataAnnotations
    0.50
    Activations Density 0.009%

    No Known Activations