© 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. 43380
    Prev
    Next
    INDEX
    Explanations

    regional areas

    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
    Regional
    -1.41
    regional
    -1.41
     regional
    -1.36
     Regional
    -1.36
     REGIONAL
    -1.28
     regionales
    -1.21
     régionale
    -1.17
    REGIONAL
    -1.11
     régional
    -1.09
     régionales
    -1.05
    POSITIVE LOGITS
    ized
    0.74
    ization
    0.68
     tope
    0.53
    ivas
    0.52
    ize
    0.51
    ical
    0.49
    っか
    0.49
     web
    0.48
     top
    0.47
     bers
    0.46
    Activations Density 0.517%

    No Known Activations