© 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. 5405
    Prev
    Next
    INDEX
    Explanations

    3

    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
     Webber
    -0.42
    ṁ
    -0.41
     Bischof
    -0.41
     Jeep
    -0.40
    ół
    -0.40
     Petru
    -0.39
    лось
    -0.39
     Toyota
    -0.38
     MAN
    -0.38
     wigs
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.81
     Wikimedijinoj
    0.80
    Билгалдахарш
    0.79
     lenker
    0.79
    CodedInputStream
    0.78
     كومونز
    0.77
    UnsafeEnabled
    0.76
     EconPapers
    0.76
    enumi
    0.75
    \{\\
    0.73
    Activations Density 0.000%

    No Known Activations