© 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. 9888
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     houſe
    -0.71
    RTLD
    -0.68
     Cæsar
    -0.63
     pleaſure
    -0.63
     Monfieur
    -0.60
     myſelf
    -0.60
     caufe
    -0.60
     Houſe
    -0.59
     חיצוניים
    -0.58
     Trit
    -0.57
    POSITIVE LOGITS
    onActivityResult
    0.60
    ly
    0.54
     समीक्षक
    0.49
     Walkover
    0.47
     تعدى
    0.46
    liferay
    0.45
    حوالہ
    0.44
    MessageOf
    0.44
    ільки
    0.43
     Roskov
    0.43
    Activations Density 0.085%

    No Known Activations