© 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. 93900
    Prev
    Next
    INDEX
    Explanations

    Dec

    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
    Dec
    -1.16
    Jul
    -1.05
     Dec
    -0.89
    Aug
    -0.83
    #+#
    -0.82
    Sep
    -0.80
    dec
    -0.78
    Feb
    -0.76
    Jun
    -0.75
    ⓧ
    -0.73
    POSITIVE LOGITS
    s
    0.52
    Gweler
    0.50
     Saltar
    0.50
    ilets
    0.49
     للمعارف
    0.49
     Anſ
    0.49
    els
    0.49
    <bos>
    0.48
    sburg
    0.47
     becauſe
    0.46
    Activations Density 1.664%

    No Known Activations