© 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. 1-CLT-HP
    7. 10292
    Prev
    Next
    INDEX
    Explanations

    university locations

    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
    H
    -0.48
     H
    -0.46
     N
    -0.45
     M
    -0.45
     P
    -0.44
    M
    -0.44
    TP
    -0.44
     L
    -0.43
     сто
    -0.43
     I
    -0.42
    POSITIVE LOGITS
     Efq
    1.13
     myſelf
    1.05
     Monfieur
    1.00
     Theſe
    0.98
     poffible
    0.97
     becauſe
    0.96
    expandindo
    0.96
     auffi
    0.93
    GEBURTSDATUM
    0.92
     Majefty
    0.90
    Activations Density 0.098%

    No Known Activations