© 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. 94780
    Prev
    Next
    INDEX
    Explanations

    pedestrian

    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
     pleaſure
    -1.33
     purpoſe
    -1.31
     ſtate
    -1.27
     ſta
    -1.25
     ſeveral
    -1.24
     Theſe
    -1.24
     Monfieur
    -1.24
     becauſe
    -1.23
     Diſ
    -1.23
     Anſ
    -1.23
    POSITIVE LOGITS
     G
    0.66
     (
    0.63
     R
    0.63
     é
    0.63
     Cap
    0.61
     
    0.60
     '
    0.60
     des
    0.60
     he
    0.59
     am
    0.58
    Activations Density 0.151%

    No Known Activations