© 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. 1-CLT-HP
    7. 14569
    Prev
    Next
    INDEX
    Explanations

    ise

    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
     ſeveral
    -0.85
     Majefty
    -0.79
     purpoſe
    -0.78
     myſelf
    -0.72
     Monfieur
    -0.71
     Reſ
    -0.71
     fubject
    -0.71
     himſelf
    -0.69
     perſon
    -0.69
     Anſ
    -0.68
    POSITIVE LOGITS
    脚注の使い方
    0.54
     kasarigan
    0.50
    Ifc
    0.48
    exitRule
    0.47
    leting
    0.46
    fting
    0.46
    featureID
    0.44
    Tembelea
    0.44
    autique
    0.44
    Халык
    0.43
    Activations Density 0.040%

    No Known Activations