© 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. 94892
    Prev
    Next
    INDEX
    Explanations

    colon

    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
    ftagPool
    -0.71
    matchCondition
    -0.70
    ніципалі
    -0.68
     estekak
    -0.66
     EconPapers
    -0.66
     Synthesis
    -0.63
    enterOuterAlt
    -0.63
    تقاوى
    -0.63
     pinulongan
    -0.62
    Jereo
    -0.61
    POSITIVE LOGITS
     He
    0.66
    onets
    0.49
    LOAT
    0.49
    ukkig
    0.49
    TargetException
    0.48
    ందు
    0.45
     His
    0.45
    sements
    0.44
    uality
    0.44
     بابا
    0.44
    Activations Density 0.026%

    No Known Activations