© 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. 15380
    Prev
    Next
    INDEX
    Explanations

    calculations

    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
    Geplaatst
    -1.06
     Normdatei
    -0.76
     Efq
    -0.75
     botanist
    -0.75
    '}>
    -0.74
     Jefus
    -0.73
     endwhile
    -0.72
     itſelf
    -0.72
     mathematicians
    -0.71
     nahilalakip
    -0.70
    POSITIVE LOGITS
     per
    0.49
     e
    0.45
     patient
    0.45
     not
    0.44
     di
    0.44
     Not
    0.44
     L
    0.43
     ε
    0.43
     voltaje
    0.43
     type
    0.42
    Activations Density 0.009%

    No Known Activations