© 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. 42437
    Prev
    Next
    INDEX
    Explanations

    science and medical terminology

    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
    mil
    -0.99
    MIL
    -0.86
    Mil
    -0.59
     MIL
    -0.56
     bin
    -0.46
     (
    -0.46
    hes
    -0.44
     anni
    -0.43
     lo
    -0.42
    hed
    -0.40
    POSITIVE LOGITS
     Efq
    1.17
     Theſe
    1.16
     myſelf
    1.13
    elemField
    1.02
     ſtate
    1.02
     itſelf
    1.00
     poffible
    0.99
     whoſe
    0.98
     Majefty
    0.98
     Eſ
    0.97
    Activations Density 1.524%

    No Known Activations