© 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. 5-CLT-HP
    7. 92634
    Prev
    Next
    INDEX
    Explanations

    •

    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
    BufferException
    -0.98
    AddTagHelper
    -0.97
    WireFormatLite
    -0.91
    出版年
    -0.89
    ValueStyle
    -0.86
    SourceChecksum
    -0.82
     defaultstate
    -0.82
    rungsseite
    -0.81
    RectangleBorder
    -0.79
     alman
    -0.79
    POSITIVE LOGITS
     avulla
    0.39
    End
    0.34
    oarece
    0.34
     Endocrinology
    0.32
     couvercle
    0.30
     End
    0.30
     Less
    0.30
     Neu
    0.29
     Onco
    0.29
    Other
    0.28
    Activations Density 0.002%

    No Known Activations