© 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. 42612
    Prev
    Next
    INDEX
    Explanations

    Mel or humor

    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
     Paglinawan
    -0.73
    UrlResolution
    -0.71
    LEncoder
    -0.69
     kasarigan
    -0.67
    idue
    -0.65
     المعيارى
    -0.63
     funny
    -0.61
    出版年
    -0.61
    AndEndTag
    -0.59
     funniest
    -0.58
    POSITIVE LOGITS
     useRouter
    0.56
    hdashline
    0.56
     Indra
    0.52
     Houſe
    0.52
     Helios
    0.52
    oğlu
    0.50
     myſelf
    0.50
    requireNonNull
    0.50
     houſe
    0.49
    Tradition
    0.49
    Activations Density 0.200%

    No Known Activations