© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92835
    Prev
    Next
    INDEX
    Explanations

    typically

    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
     typically
    -1.34
     Typically
    -1.20
    typically
    -1.16
    Typically
    -1.15
    utility
    -1.02
     utility
    -0.94
     tend
    -0.91
     tends
    -0.90
    Utility
    -0.87
     normalmente
    -0.87
    POSITIVE LOGITS
     not
    0.59
     to
    0.58
    פור
    0.43
    ीय
    0.41
     NOT
    0.40
    Portail
    0.39
    Lähteet
    0.38
    پار
    0.38
    not
    0.37
    ing
    0.37
    Activations Density 1.085%

    No Known Activations