© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75916
    Prev
    Next
    INDEX
    Explanations

    Chemical and biological processes

    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
    SourceChecksum
    -0.63
     hyal
    -0.55
     skim
    -0.55
     dex
    -0.53
    pyplot
    -0.52
     hex
    -0.51
    حياتها
    -0.50
    GrantedAuthority
    -0.50
     Leite
    -0.48
    tagHelperRunner
    -0.48
    POSITIVE LOGITS
    findpost
    0.57
    клопе
    0.56
     AspNetCore
    0.52
     ModelExpression
    0.50
    meanor
    0.48
     GOB
    0.47
     COB
    0.47
    obos
    0.46
    enschaft
    0.46
    InputBorder
    0.46
    Activations Density 0.012%

    No Known Activations