© 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. 91624
    Prev
    Next
    INDEX
    Explanations

    summaries and space

    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
     ju
    -0.42
     přes
    -0.41
    cy
    -0.41
    ColumnHeaders
    -0.41
    ieux
    -0.41
    InThe
    -0.41
    Readable
    -0.41
    jini
    -0.41
    ítě
    -0.40
     '../../../../
    -0.40
    POSITIVE LOGITS
     مرئيه
    0.90
     يتيمه
    0.84
    BufferException
    0.77
     للمعارف
    0.74
    ruptedException
    0.74
    saraba
    0.73
    InjectAttribute
    0.72
     endwhile
    0.70
    MigrationBuilder
    0.70
     MainAxisSize
    0.69
    Activations Density 0.000%

    No Known Activations