© 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. 5-CLT-HP
    7. 92558
    Prev
    Next
    INDEX
    Explanations

    snorkel

    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
     GoogleFonts
    -0.75
     defStyleAttr
    -0.69
    twimg
    -0.66
    interopRequire
    -0.66
    cshtml
    -0.65
     ContentValues
    -0.64
    __(/*!
    -0.64
    enumii
    -0.63
    ymce
    -0.62
     Instruments
    -0.61
    POSITIVE LOGITS
     الرياضيه
    0.58
     holidays
    0.47
     vacations
    0.47
    viewing
    0.46
     Meksiku
    0.44
     scoper
    0.42
     adventures
    0.41
    adventures
    0.41
     viewing
    0.40
    feuer
    0.40
    Activations Density 0.001%

    No Known Activations