© 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. 92684
    Prev
    Next
    INDEX
    Explanations

    i

    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
     للمعارف
    -0.51
    bitol
    -0.43
    izing
    -0.42
    ize
    -0.41
    trou
    -0.40
     jaką
    -0.40
     možno
    -0.39
    kauf
    -0.39
    evt
    -0.39
    oles
    -0.39
    POSITIVE LOGITS
     الحره
    0.73
    IVEREF
    0.68
    qrstuvwxyz
    0.67
    abestanden
    0.63
    AddWithValue
    0.62
    notNull
    0.62
    hoeddwyd
    0.59
    ollectionView
    0.57
    AttributeSet
    0.57
    ADVERTISEMENT
    0.56
    Activations Density 0.014%

    No Known Activations