© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1207
    Prev
    Next
    INDEX
    Explanations

    arises

    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
     aidé
    -0.67
     livré
    -0.65
     genoux
    -0.64
    Дереккөздер
    -0.57
     volgende
    -0.57
     Betracht
    -0.56
     refusé
    -0.56
     contribué
    -0.55
     suivante
    -0.54
     suivants
    -0.54
    POSITIVE LOGITS
     a
    1.41
     the
    1.15
     an
    1.01
     those
    0.89
     what
    0.85
     their
    0.74
     something
    0.73
    LookAnd
    0.71
     another
    0.71
     our
    0.68
    Activations Density 0.001%

    No Known Activations