© 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. 20-CLT-HP
    7. 71951
    Prev
    Next
    INDEX
    Explanations

    technical/research text

    np_max-act-logits · 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
    الحياه
    -0.90
    RegistryLite
    -0.81
    IntoConstraints
    -0.80
    LookAnd
    -0.79
     >=",
    -0.74
     للمعارف
    -0.73
    ciutto
    -0.73
    saraba
    -0.73
    TagHelper
    -0.72
     BrowserModule
    -0.71
    POSITIVE LOGITS
     with
    0.59
     in
    0.57
    with
    0.56
     dengan
    0.41
    Background
    0.40
    tazione
    0.39
    ňte
    0.38
    jooq
    0.38
    斗
    0.37
     avec
    0.36
    Activations Density 0.008%

    No Known Activations