© 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. 72805
    Prev
    Next
    INDEX
    Explanations

    Free

    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
     تضيفلها
    -0.67
    matchCondition
    -0.62
    tagext
    -0.62
    RegistryLite
    -0.62
    WebElementEntity
    -0.59
    حياته
    -0.57
     disambiguazione
    -0.55
    DebuggerNonUser
    -0.55
    awtextra
    -0.55
    ///</
    -0.54
    POSITIVE LOGITS
     isolato
    0.67
     isolado
    0.59
    BASIC
    0.58
    tahankan
    0.57
     básico
    0.56
     généraux
    0.55
     brancas
    0.53
     betrekking
    0.53
     africains
    0.52
     dourada
    0.52
    Activations Density 0.009%

    No Known Activations