© 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. 14792
    Prev
    Next
    INDEX
    Explanations

    serve

    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
    EndContext
    -0.51
     XHTML
    -0.46
     DataLoader
    -0.45
    xtext
    -0.45
     morire
    -0.45
    SDI
    -0.45
     myſelf
    -0.44
     liné
    -0.44
    ApiModel
    -0.43
     aimable
    -0.43
    POSITIVE LOGITS
    mappedBy
    0.59
     a
    0.59
    etary
    0.57
     propOrder
    0.56
     &___
    0.55
    gway
    0.53
     ویکی‌پدی
    0.52
    ancies
    0.52
    ölkerung
    0.51
     legal
    0.51
    Activations Density 0.009%

    No Known Activations