© 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. 1-CLT-HP
    7. 15794
    Prev
    Next
    INDEX
    Explanations

    orph

    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
     marshmallows
    -0.96
     marshmallow
    -0.75
     FetchType
    -0.68
    WebVitals
    -0.64
     MainAxisSize
    -0.60
     Prim
    -0.59
    出版年
    -0.59
     تضيفلها
    -0.58
    tonode
    -0.58
     själva
    -0.57
    POSITIVE LOGITS
    ifter
    0.52
    brokes
    0.52
    strar
    0.50
    ble
    0.50
    脚注の使い方
    0.49
    atar
    0.48
    bey
    0.48
    tak
    0.48
    ant
    0.47
    bit
    0.45
    Activations Density 0.120%

    No Known Activations