© 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. 94495
    Prev
    Next
    INDEX
    Explanations

    dichoto

    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
     myſelf
    -0.88
     stiefel
    -0.87
     purpoſe
    -0.85
     ſtate
    -0.84
     moschino
    -0.80
     Spaniard
    -0.80
     Monfieur
    -0.78
     ſtand
    -0.78
     ſta
    -0.78
     fevere
    -0.77
    POSITIVE LOGITS
     Per
    0.53
     Ber
    0.49
     Bl
    0.49
     Wil
    0.49
     Pal
    0.48
     Bra
    0.47
    KommentareTeilen
    0.46
     br
    0.45
     per
    0.44
     ber
    0.44
    Activations Density 1.774%

    No Known Activations