© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3748
    Prev
    Next
    INDEX
    Explanations

    adding

    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
    ftagPool
    -0.63
    ]--;
    -0.55
    IsMutable
    -0.52
    ']?>
    -0.51
    횟
    -0.51
    ItemBackground
    -0.50
     ویکی‌پدیای
    -0.49
    InjectAttribute
    -0.49
     spins
    -0.49
    abestanden
    -0.48
    POSITIVE LOGITS
     bahwa
    0.64
    WEBPACK
    0.60
    VersionUID
    0.59
    ViewInit
    0.59
     that
    0.59
     bahawa
    0.56
     ότι
    0.55
    ActionCreators
    0.54
     enfans
    0.54
    spyOn
    0.54
    Activations Density 0.000%

    No Known Activations