© 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. 0-CLT-HP
    7. 42301
    Prev
    Next
    INDEX
    Explanations

    coming, in progress

    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
    ########.
    -0.95
     choices
    -0.90
    ^(@)
    -0.84
     iconFacebook
    -0.78
     للاسماء
    -0.76
     Fresco
    -0.75
    ſelves
    -0.73
     Forumite
    -0.72
    出版年
    -0.71
    enumi
    -0.71
    POSITIVE LOGITS
     of
    0.57
    '
    0.51
    ’
    0.51
    how
    0.48
     would
    0.46
     for
    0.44
    mane
    0.43
     will
    0.43
    for
    0.42
     moment
    0.41
    Activations Density 0.025%

    No Known Activations