© 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. 1341
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    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
     nack
    -0.59
    centage
    -0.57
    ModelSerializer
    -0.54
    ."));
    -0.53
    zinger
    -0.53
    kelt
    -0.53
    cluding
    -0.53
    .")]
    -0.52
     ihop
    -0.52
    nappropriate
    -0.52
    POSITIVE LOGITS
     substantially
    0.59
     dramatically
    0.58
     significantly
    0.57
    ifikant
    0.53
     considerably
    0.52
     výraz
    0.52
     generously
    0.50
    titleMargin
    0.50
     markedly
    0.50
    Tikang
    0.49
    Activations Density 0.003%

    No Known Activations