© 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. 1-CLT-HP
    7. 13808
    Prev
    Next
    INDEX
    Explanations

    Br

    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
     Br
    -1.27
    Br
    -1.13
     '\\;'
    -0.76
     br
    -0.75
    GeneratedCode
    -0.68
    protoimpl
    -0.67
    br
    -0.65
     Brü
    -0.63
     onAnimation
    -0.61
     ModelExpression
    -0.60
    POSITIVE LOGITS
     consec
    0.51
     cytoplasm
    0.49
    Octopus
    0.48
    expandindo
    0.47
    Instrument
    0.47
     vuitton
    0.47
    ScopeManager
    0.47
     misura
    0.47
     superstructure
    0.45
     phénomène
    0.44
    Activations Density 0.015%

    No Known Activations