© 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. 20-CLT-HP
    7. 77043
    Prev
    Next
    INDEX
    Explanations

    run

    np_max-act-logits · 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
    oredCriteria
    -0.69
     <=",
    -0.68
    /*
    -0.63
     саны
    -0.62
     '\\;'
    -0.62
     ***!
    -0.59
    Externé
    -0.59
    حوالہ
    -0.58
     Ease
    -0.57
     PARSER
    -0.57
    POSITIVE LOGITS
     am
    0.92
     amo
    0.85
     rough
    0.81
    am
    0.75
     rings
    0.72
     wild
    0.66
    AM
    0.66
    Am
    0.65
    rough
    0.58
     Am
    0.58
    Activations Density 0.001%

    No Known Activations