© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94139
    Prev
    Next
    INDEX
    Explanations

    Pinot

    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
    ContentAlignment
    -0.55
    ovka
    -0.52
    lacian
    -0.51
    getMenuInflater
    -0.51
    URBANA
    -0.49
    LLAB
    -0.49
    Jeho
    -0.49
    Owners
    -0.48
    IJ
    -0.48
    InputBorder
    -0.48
    POSITIVE LOGITS
     Noir
    0.59
     שוליים
    0.52
     Grig
    0.50
    Lähteet
    0.50
     referenties
    0.47
    Šaltiniai
    0.45
     Noi
    0.44
     Neri
    0.44
    PYX
    0.43
     GeoNames
    0.43
    Activations Density 0.001%

    No Known Activations