© 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. 0-CLT-HP
    7. 95168
    Prev
    Next
    INDEX
    Explanations

    technical/numerical documents

    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
     Markup
    -1.53
     getItemCount
    -0.68
     Италијани
    -0.67
    Markup
    -0.65
    脚注の使い方
    -0.63
    addCriterion
    -0.59
    endphp
    -0.57
    reicht
    -0.57
    Parcelize
    -0.57
     heapq
    -0.56
    POSITIVE LOGITS
    IVEREF
    0.52
     Function
    0.50
    تقاوى
    0.47
    delin
    0.46
    нём
    0.45
    fein
    0.45
    données
    0.43
     complete
    0.43
    SpringRunner
    0.43
     encomp
    0.42
    Activations Density 0.240%

    No Known Activations