© 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. 76998
    Prev
    Next
    INDEX
    Explanations

    Sel

    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
     disambiguazione
    -0.80
    RTEX
    -0.71
    archiviato
    -0.70
    Hochspringen
    -0.68
    SequentialGroup
    -0.68
    RetentionPolicy
    -0.67
    Ecotoxicity
    -0.66
    
    -0.66
    RuleContext
    -0.65
     createState
    -0.64
    POSITIVE LOGITS
     ausgeschlossen
    0.43
    withIdentifier
    0.39
    ()]
    0.39
    onsored
    0.38
    Narrator
    0.38
    InitStruct
    0.37
     Greenville
    0.37
     Art
    0.37
     art
    0.36
     themselves
    0.36
    Activations Density 0.000%

    No Known Activations