© 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. 5-CLT-HP
    7. 3870
    Prev
    Next
    INDEX
    Explanations

    of

    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
    rungsseite
    -0.58
    udin
    -0.53
    Enllaços
    -0.50
    ệm
    -0.49
     bienfaits
    -0.49
     attentes
    -0.48
    VersionUID
    -0.48
    EndContext
    -0.48
    '&:
    -0.47
     dimensioni
    -0.47
    POSITIVE LOGITS
    CppCodeGen
    0.59
     <<<<<<<<<<<<<<
    0.57
     '\\;'
    0.53
     the
    0.53
     future
    0.52
     existing
    0.50
     Partagez
    0.50
     الاطلاع
    0.50
    
    0.48
    drawSprites
    0.48
    Activations Density 0.003%

    No Known Activations