© 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. 91853
    Prev
    Next
    INDEX
    Explanations

    Complicated problems/situations

    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
     Winaray
    -0.57
     cucharadas
    -0.54
     pés
    -0.52
    with
    -0.51
    aarrggbb
    -0.49
    both
    -0.48
    plain
    -0.47
    already
    -0.47
    an
    -0.47
    like
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.73
    expandindo
    0.67
     ویکی‌پدیا
    0.63
    Демографія
    0.58
    Према
    0.57
    AccessorTable
    0.56
    ratulations
    0.53
    XmlAccessorType
    0.53
    aderie
    0.53
    InSection
    0.50
    Activations Density 0.002%

    No Known Activations