© 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. 0-CLT-HP
    7. 93765
    Prev
    Next
    INDEX
    Explanations

    conditioned

    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
     conditioned
    -1.05
    conditioned
    -0.98
    rez
    -0.77
    en
    -0.66
    nter
    -0.66
    REZ
    -0.62
    rxjs
    -0.52
    loe
    -0.49
    uded
    -0.48
    es
    -0.47
    POSITIVE LOGITS
     itſelf
    1.00
     Roskov
    0.96
     ModelExpression
    0.94
     poffible
    0.91
     Majefty
    0.91
     myſelf
    0.90
     ་་
    0.88
     auffi
    0.87
     ſeveral
    0.87
     Efq
    0.86
    Activations Density 0.214%

    No Known Activations