© 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. 94281
    Prev
    Next
    INDEX
    Explanations

    wide

    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
     wide
    -3.14
     Wide
    -2.69
    Wide
    -2.56
    wide
    -2.48
     WIDE
    -2.39
     wider
    -2.22
     widest
    -2.11
    WIDE
    -1.98
     Wider
    -1.59
    wider
    -1.58
    POSITIVE LOGITS
    TagMode
    0.66
    ViewStyle
    0.59
    acre
    0.54
    enough
    0.53
    epik
    0.53
    -
    0.51
    LLocation
    0.50
     lease
    0.49
    staticmethod
    0.49
    hurst
    0.48
    Activations Density 0.156%

    No Known Activations