© 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. 0-CLT-HP
    7. 94917
    Prev
    Next
    INDEX
    Explanations

    take

    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
     will
    -0.81
     zullen
    -0.64
     sẽ
    -0.63
     будут
    -0.56
    Will
    -0.56
     sarà
    -0.55
    will
    -0.54
     będzie
    -0.54
     zostanie
    -0.54
    gameserver
    -0.53
    POSITIVE LOGITS
     tartalomajánló
    0.70
    parsedMessage
    0.66
     AssemblyCulture
    0.61
    CrossRef
    0.59
     yı
    0.59
     anything
    0.56
     Administrativna
    0.56
    tover
    0.53
    SPATH
    0.52
    RegressionTest
    0.52
    Activations Density 0.444%

    No Known Activations