© 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. 14349
    Prev
    Next
    INDEX
    Explanations

    metal

    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
     courants
    -0.68
     Dance
    -0.58
    ensed
    -0.57
     anledning
    -0.57
    Bored
    -0.56
     problemet
    -0.56
    Poloha
    -0.55
    sad
    -0.54
    valget
    -0.54
    afe
    -0.54
    POSITIVE LOGITS
    MethodManager
    0.46
    mybatisplus
    0.45
     للاسماء
    0.45
    ImGui
    0.43
    MemoryWarning
    0.43
    istan
    0.43
     heavens
    0.42
     detectors
    0.42
     JADX
    0.42
    ModelAdmin
    0.42
    Activations Density 0.066%

    No Known Activations