© 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. 5-CLT-HP
    7. 98034
    Prev
    Next
    INDEX
    Explanations

    World War I or II

    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
    enumii
    -0.66
    OCCURRED
    -0.51
    Искәрмәләр
    -0.50
    UpInside
    -0.50
    Collegamenti
    -0.48
    RenderAtEndOf
    -0.48
     EClass
    -0.46
     GenerationType
    -0.46
    ToMany
    -0.44
    Ран
    -0.44
    POSITIVE LOGITS
    rungsseite
    0.92
    Rüyada
    0.71
    <bos>
    0.60
    binaan
    0.57
     whereof
    0.56
     Allociné
    0.56
    LookAnd
    0.55
    Похо
    0.54
    belajaran
    0.53
     Merle
    0.52
    Activations Density 0.002%

    No Known Activations