© 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. 0-CLT-HP
    7. 94453
    Prev
    Next
    INDEX
    Explanations

    ropolitan

    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
     under
    -0.70
     Under
    -0.61
    Under
    -0.60
     underneath
    -0.59
    under
    -0.54
     beneath
    -0.52
     serving
    -0.51
     sotto
    -0.46
     UNDER
    -0.45
    UNDER
    -0.44
    POSITIVE LOGITS
    windowFixed
    1.16
    SharedCtor
    0.96
     surla
    0.91
    tvguidetime
    0.89
    
    0.88
    enterOuterAlt
    0.86
     propOrder
    0.86
     HasFactory
    0.84
     Efq
    0.83
     AppCompatTheme
    0.79
    Activations Density 1.393%

    No Known Activations