© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1324
    Prev
    Next
    INDEX
    Explanations

    2

    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
     дописавши
    -0.70
    udesta
    -0.63
    ########.
    -0.58
     دریافت‌شده
    -0.57
    ularia
    -0.57
    jén
    -0.56
     FBref
    -0.56
    styleUrls
    -0.56
    enumi
    -0.55
     reconno
    -0.54
    POSITIVE LOGITS
    LookAnd
    0.62
     كومونز
    0.60
    HeaderText
    0.53
    DoubleQuotes
    0.51
    bootstrapcdn
    0.49
    aarrggbb
    0.46
    UnknownFieldSet
    0.45
    SharedDtor
    0.43
    OrBuilder
    0.43
     Stras
    0.42
    Activations Density 0.003%

    No Known Activations