© 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. 76412
    Prev
    Next
    INDEX
    Explanations

    Code, names, unusual words

    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
    ote
    -0.49
     Cycle
    -0.48
    Morfologia
    -0.47
     cycle
    -0.47
    ExtendWith
    -0.46
     stel
    -0.45
    TProtocol
    -0.45
     Object
    -0.44
     object
    -0.44
     predeceased
    -0.44
    POSITIVE LOGITS
    BufferException
    0.59
    yntaxException
    0.58
    adaptiveStyles
    0.54
     disambiguazione
    0.54
    IonicModule
    0.53
     nakalista
    0.52
    Tikang
    0.50
    umbuhan
    0.50
    principalColumn
    0.49
    tipation
    0.49
    Activations Density 0.000%

    No Known Activations