© 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. 42409
    Prev
    Next
    INDEX
    Explanations

    done

    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
     done
    -0.95
    done
    -0.90
     Done
    -0.83
    Done
    -0.75
    AddTagHelper
    -0.65
     DONE
    -0.65
    usammen
    -0.65
     getan
    -0.63
     gedaan
    -0.61
     tartalomajánló
    -0.60
    POSITIVE LOGITS
     that
    0.60
    ”
    0.59
    “
    0.58
    ’
    0.56
     for
    0.55
    __*/
    0.54
     nakalista
    0.51
     in
    0.51
     שוליים
    0.51
     “
    0.50
    Activations Density 0.101%

    No Known Activations