© 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. 93520
    Prev
    Next
    INDEX
    Explanations

    workflow

    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
    FTFY
    -0.94
    =$?
    -0.86
     nakalista
    -0.86
    NUMX
    -0.82
     BRARY
    -0.81
    GEBURTSDATUM
    -0.81
     IBRARY
    -0.80
    strtotime
    -0.74
    BibitemShut
    -0.73
     Efq
    -0.72
    POSITIVE LOGITS
    ed
    0.98
    s
    0.92
    e
    0.74
    i
    0.73
    es
    0.70
    y
    0.63
    ing
    0.63
    u
    0.58
    med
    0.58
    .
    0.57
    Activations Density 0.994%

    No Known Activations