© 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. 5-CLT-HP
    7. 97574
    Prev
    Next
    INDEX
    Explanations

    is

    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
     had
    -0.49
     would
    -0.46
    σιμοποι
    -0.43
     <>",
    -0.43
     avrebbero
    -0.41
    sburg
    -0.41
     came
    -0.40
    moreland
    -0.40
     hadn
    -0.39
    came
    -0.39
    POSITIVE LOGITS
     nahilalakip
    0.86
    parsedMessage
    0.85
     to
    0.77
    DoubleQuotes
    0.68
    JsonInclude
    0.68
    pportun
    0.64
    OGND
    0.63
    ViewFeatures
    0.61
    dhist
    0.59
     Osiris
    0.59
    Activations Density 0.003%

    No Known Activations