© 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. 5-CLT-HP
    7. 5397
    Prev
    Next
    INDEX
    Explanations

    good

    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
    falls
    -0.50
    par
    -0.47
     vå
    -0.47
    <bos>
    -0.46
     حد
    -0.45
    fall
    -0.45
    park
    -0.44
     انداز
    -0.43
     in
    -0.43
    fallen
    -0.42
    POSITIVE LOGITS
    Hauptartikel
    0.74
     فريبيس
    0.73
     nahilalakip
    0.69
    Rhestr
    0.68
    InitVars
    0.67
    ########.
    0.67
    +:+
    0.67
    $)$
    0.66
    Hochspringen
    0.65
    hyrchwyd
    0.65
    Activations Density 0.000%

    No Known Activations