© 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. 4785
    Prev
    Next
    INDEX
    Explanations

    Start of a declaration/article

    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
     Normdatei
    -0.91
     disambiguazione
    -0.89
    OrBuilder
    -0.81
    tagHelperRunner
    -0.79
     EconPapers
    -0.69
    awtextra
    -0.68
    وعة
    -0.67
     الحره
    -0.67
    SharedCtor
    -0.66
    ChildIndex
    -0.66
    POSITIVE LOGITS
     Erfüllung
    0.44
    ियन
    0.40
    miljø
    0.38
     оригіналу
    0.36
    ışık
    0.36
     Fitting
    0.35
     köy
    0.34
    spraak
    0.34
     atve
    0.34
     habitants
    0.34
    Activations Density 0.000%

    No Known Activations