© 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. 20-CLT-HP
    7. 73359
    Prev
    Next
    INDEX
    Explanations

    Names and/or code

    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
    \{\\
    -0.90
    +#+#
    -0.85
    Geplaatst
    -0.82
    ніципа
    -0.81
    verifyException
    -0.77
    ngdoc
    -0.75
    SerializedSize
    -0.74
    tagext
    -0.73
     écoulé
    -0.73
     gee
    -0.73
    POSITIVE LOGITS
     appel
    0.36
    brite
    0.34
    માં
    0.31
    ổ
    0.31
    <h4>
    0.31
    úp
    0.29
     aank
    0.29
    UP
    0.29
    út
    0.29
    stron
    0.29
    Activations Density 0.003%

    No Known Activations