© 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. 42939
    Prev
    Next
    INDEX
    Explanations

    background details

    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
    tagext
    -0.72
     EdgeInsets
    -0.67
    ReusableCell
    -0.67
     réunis
    -0.66
     незавершена
    -0.66
    lindungan
    -0.64
     carreaux
    -0.63
    IGraphics
    -0.63
    Hochspringen
    -0.62
     ddelweddau
    -0.62
    POSITIVE LOGITS
     all
    0.63
    -
    0.54
     in
    0.53
    r
    0.53
    ty
    0.48
     being
    0.48
    Билгалдахарш
    0.46
     well
    0.46
     (
    0.45
    ある
    0.45
    Activations Density 0.113%

    No Known Activations