© 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. 5-CLT-HP
    7. 97988
    Prev
    Next
    INDEX
    Explanations

    time passing

    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
    íritu
    -0.52
    lynol
    -0.50
     ticks
    -0.50
    loze
    -0.49
    pleasure
    -0.47
    ît
    -0.47
    componentWill
    -0.46
     Auft
    -0.46
    tiko
    -0.46
     Virtual
    -0.45
    POSITIVE LOGITS
     للمعارف
    1.04
     without
    0.75
     since
    0.67
    GraphicsUnit
    0.66
    henswürdigkeiten
    0.64
    uxxxx
    0.63
    脚注の使い方
    0.61
    HtmlAttribute
    0.60
    RegistryLite
    0.60
     roues
    0.59
    Activations Density 0.001%

    No Known Activations