© 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. 20-CLT-HP
    7. 72593
    Prev
    Next
    INDEX
    Explanations

    explains

    np_max-act-logits · 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
     élas
    -0.70
     duquel
    -0.69
     errori
    -0.67
     médicaux
    -0.63
    ResponseWriter
    -0.62
    ostante
    -0.62
     polaire
    -0.62
    SBATCH
    -0.60
     rapides
    -0.60
     alluminio
    -0.60
    POSITIVE LOGITS
     of
    0.90
     in
    0.67
     from
    0.61
    makeText
    0.58
     found
    0.52
    исленность
    0.50
    ]]=
    0.49
     built
    0.48
     on
    0.46
     levied
    0.46
    Activations Density 0.002%

    No Known Activations