© 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. 4512
    Prev
    Next
    INDEX
    Explanations

    concluding remarks

    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
     scolaires
    -0.54
     pitä
    -0.53
     waarin
    -0.53
    zości
    -0.52
     собою
    -0.52
    tvguidetime
    -0.51
     Saltar
    -0.51
     apareceu
    -0.51
     daß
    -0.50
     auraient
    -0.50
    POSITIVE LOGITS
    UnusedPrivate
    0.64
    WindowConstants
    0.59
    TintMode
    0.56
     again
    0.54
    insee
    0.54
    createCanvas
    0.53
    ungalow
    0.52
    HideFlags
    0.52
     برانيه
    0.51
    BoxLayout
    0.51
    Activations Density 0.000%

    No Known Activations