© 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. 94196
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    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
    IsMutable
    -0.86
     challenging
    -0.78
    intuitive
    -0.78
     rewarding
    -0.76
     Challenging
    -0.75
     pioneer
    -0.69
     gathered
    -0.69
    TintMode
    -0.69
    ьаж
    -0.68
    ViewImports
    -0.68
    POSITIVE LOGITS
    cos
    0.45
     math
    0.44
    ly
    0.42
    CrossRef
    0.42
    StoryboardSegue
    0.42
    יוחד
    0.41
    brigens
    0.40
    Wr
    0.40
     Conclusions
    0.40
     IR
    0.39
    Activations Density 0.034%

    No Known Activations