© 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. 72965
    Prev
    Next
    INDEX
    Explanations

    Legal/business contexts

    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
    Personendaten
    -0.66
    newswire
    -0.56
    ровок
    -0.54
    otide
    -0.52
    oneofs
    -0.50
     ProtoMessage
    -0.50
     <<<<<<<<<<<<<<
    -0.49
    тьяна
    -0.48
    saraba
    -0.47
    cinated
    -0.47
    POSITIVE LOGITS
    UrlResolution
    0.54
     cohomology
    0.51
     CUCET
    0.51
    thouses
    0.50
    #!/
    0.49
     pursuance
    0.48
    cstdio
    0.48
     onlyOwner
    0.47
    createTextNode
    0.46
    parseColor
    0.46
    Activations Density 0.000%

    No Known Activations