© 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. 15525
    Prev
    Next
    INDEX
    Explanations

    new old

    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
     old
    -1.19
    old
    -1.00
    Old
    -0.98
    OLD
    -0.98
     OLD
    -0.97
     vecchi
    -0.94
     vieille
    -0.93
     Old
    -0.91
     vieux
    -0.90
     velha
    -0.89
    POSITIVE LOGITS
    .
    0.63
     both
    0.57
    <bos>
    0.56
     has
    0.50
     of
    0.48
     that
    0.48
     among
    0.48
     is
    0.47
    agisse
    0.47
     without
    0.46
    Activations Density 0.064%

    No Known Activations