© 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. 9866
    Prev
    Next
    INDEX
    Explanations

    violence

    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
    RequestParam
    -0.49
     placement
    -0.48
     para
    -0.45
     calculating
    -0.44
     replacement
    -0.43
     jul
    -0.42
    ItemGroup
    -0.41
    dech
    -0.40
    ExecutionContext
    -0.40
     collo
    -0.40
    POSITIVE LOGITS
     المعيارى
    0.96
     متعلقه
    0.73
     esprits
    0.72
     econômica
    0.65
     colère
    0.65
     Drapeau
    0.65
     mères
    0.65
    ContentAsync
    0.65
    GEBURTSDATUM
    0.65
    AsUp
    0.64
    Activations Density 0.008%

    No Known Activations