© 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. 94875
    Prev
    Next
    INDEX
    Explanations

    Flu

    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
    unda
    -0.87
     bağlantılar
    -0.81
    +#+#
    -0.73
     חיצוניים
    -0.70
    gonic
    -0.67
    mappedBy
    -0.64
    Predecesor
    -0.64
    verwijspagina
    -0.63
    ISupport
    -0.62
     Matri
    -0.62
    POSITIVE LOGITS
    eated
    0.59
    ing
    0.52
    kloped
    0.48
    hilfe
    0.47
    e
    0.47
     ویکی‌پدی
    0.47
    styrelsen
    0.47
     pousse
    0.46
    dflare
    0.45
    paksa
    0.44
    Activations Density 0.583%

    No Known Activations