© 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. 0-CLT-HP
    7. 92848
    Prev
    Next
    INDEX
    Explanations

    cod

    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
    losis
    -1.08
     cod
    -0.90
    ctibles
    -0.80
    emy
    -0.74
    ed
    -0.63
     Cod
    -0.63
     calculators
    -0.57
    ReusableCell
    -0.56
    Cod
    -0.53
    Cubit
    -0.52
    POSITIVE LOGITS
     препратки
    0.95
    IsMutable
    0.71
     szóci
    0.70
     estekak
    0.68
    ensement
    0.65
    fjspx
    0.64
     AssemblyCulture
    0.63
    VERTISEMENT
    0.62
    protoc
    0.61
    Diwedd
    0.60
    Activations Density 1.358%

    No Known Activations