© 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. 91240
    Prev
    Next
    INDEX
    Explanations

    and

    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
     might
    -0.62
     may
    -0.62
     are
    -0.60
     must
    -0.58
     will
    -0.57
     shall
    -0.57
    ]--;
    -0.57
     were
    -0.57
     aren
    -0.57
     is
    -0.56
    POSITIVE LOGITS
     Abroad
    0.73
     financière
    0.63
     برانيه
    0.63
     enfans
    0.62
     pédagogique
    0.61
     supplémentaires
    0.60
     Around
    0.60
     quelcon
    0.59
     rêves
    0.59
     financières
    0.58
    Activations Density 0.003%

    No Known Activations