© 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. 4740
    Prev
    Next
    INDEX
    Explanations

    during

    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
     Himo
    -0.46
    ymce
    -0.45
     morire
    -0.45
     déchets
    -0.44
    cius
    -0.42
     respeito
    -0.42
    Both
    -0.42
     soutient
    -0.41
    MathML
    -0.41
    cloudflare
    -0.41
    POSITIVE LOGITS
    Diwedd
    0.76
     prior
    0.72
     previous
    0.67
    σιμοποι
    0.63
     AttributeSet
    0.63
     Prior
    0.61
    Prior
    0.61
    moiselle
    0.61
     الرياضيه
    0.60
    GroupLayout
    0.59
    Activations Density 0.002%

    No Known Activations