© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93257
    Prev
    Next
    INDEX
    Explanations

    reasons sources

    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
     Efq
    -0.98
     myſelf
    -0.88
     Shaksp
    -0.78
     Jefus
    -0.77
     itſelf
    -0.75
     himſelf
    -0.72
     moschino
    -0.72
    Portale
    -0.71
     vectorstock
    -0.71
     purpoſe
    -0.71
    POSITIVE LOGITS
     for
    0.86
    AnchorStyles
    0.60
    __*/
    0.59
     single
    0.58
    writeField
    0.57
     by
    0.56
     tell
    0.56
     typelib
    0.55
     exist
    0.54
     below
    0.54
    Activations Density 0.051%

    No Known Activations