© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2554
    Prev
    Next
    INDEX
    Explanations

    trends

    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
    SharedCtor
    -0.54
     façons
    -0.48
     préférence
    -0.47
    ására
    -0.47
    liability
    -0.45
    providedIn
    -0.45
     Chancen
    -0.45
     orig
    -0.44
     meman
    -0.44
    Демографія
    -0.44
    POSITIVE LOGITS
    NameInMap
    0.93
    الحياه
    0.61
    ScopeManager
    0.61
    EndContext
    0.59
    tagHelperRunner
    0.59
     Normdatei
    0.56
    FunctionFlags
    0.55
    fillType
    0.55
     propOrder
    0.51
     tetrachloride
    0.50
    Activations Density 0.008%

    No Known Activations