© 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. 91571
    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
    parsedMessage
    -0.88
    /*
    -0.79
    tagHelperRunner
    -0.73
     оригіналу
    -0.66
    contentLoaded
    -0.64
    <!--[
    -0.63
     '\\;'
    -0.63
    tanleria
    -0.62
     Mover
    -0.60
    הערות
    -0.59
    POSITIVE LOGITS
    ref
    0.55
     sign
    0.54
    REF
    0.48
    sign
    0.46
     Charlene
    0.45
    AxisAlignment
    0.44
    าล
    0.44
     Linde
    0.42
    Lf
    0.40
    Sign
    0.39
    Activations Density 0.017%

    No Known Activations