© 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. 0-CLT-HP
    7. 92829
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical contexts

    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
     Goliath
    -1.53
    liath
    -0.75
    Skocz
    -0.56
    ification
    -0.55
    ized
    -0.47
    ization
    -0.47
    ize
    -0.47
    ified
    -0.47
    Sponsor
    -0.46
     vaid
    -0.45
    POSITIVE LOGITS
     WaitForSeconds
    0.74
    UserScript
    0.71
    contentLoaded
    0.68
    Rujuakan
    0.62
     Kese
    0.61
     Waters
    0.61
    stem
    0.61
     Indicators
    0.60
     tenue
    0.59
     SIMBAD
    0.59
    Activations Density 2.188%

    No Known Activations