© 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. 1-CLT-HP
    7. 10635
    Prev
    Next
    INDEX
    Explanations

    REAL

    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
    bootstrapcdn
    -0.62
    gantian
    -0.58
     ويكيميديا
    -0.57
     Hippo
    -0.54
     bóng
    -0.54
    InputTagHelper
    -0.53
     BATTERY
    -0.52
    antation
    -0.52
     lccn
    -0.52
    Palabras
    -0.50
    POSITIVE LOGITS
    WireFormatLite
    0.56
    ɵɵelementEnd
    0.54
     Audiodateien
    0.52
    今から
    0.47
     Grüsse
    0.47
    USP
    0.46
     jura
    0.45
     resources
    0.45
    thunk
    0.44
    Skocz
    0.44
    Activations Density 0.039%

    No Known Activations