© 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. 1-CLT-HP
    7. 15010
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    ViewImports
    -0.85
    IndentedString
    -0.82
    IsMutable
    -0.80
    elemField
    -0.78
     propOrder
    -0.76
    
    -0.76
    setVerticalGroup
    -0.75
    Personendaten
    -0.75
    AndEndTag
    -0.75
    InstrumentedTest
    -0.73
    POSITIVE LOGITS
    x
    0.55
    b
    0.54
    a
    0.53
    4
    0.51
    h
    0.49
    str
    0.48
    ub
    0.48
    ot
    0.48
    mb
    0.46
     thought
    0.46
    Activations Density 0.252%

    No Known Activations