© 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. 4-CLT-HP
    7. 1820
    Prev
    Next
    INDEX
    Explanations

    establish

    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
    expandindo
    -0.65
     समीक्षक
    -0.65
    fras
    -0.56
     مرئيه
    -0.56
    GIVEREF
    -0.55
    enderror
    -0.55
    charCodeAt
    -0.55
     endblock
    -0.54
     незавершена
    -0.54
    windowFixed
    -0.54
    POSITIVE LOGITS
    complexContent
    0.67
     EXPECT
    0.48
     صوتيه
    0.47
    SOUNDBITE
    0.46
    AxisAlignment
    0.46
     Expected
    0.46
     WHICH
    0.45
    sizeCache
    0.45
    :✨
    0.45
     existence
    0.44
    Activations Density 0.007%

    No Known Activations