© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93077
    Prev
    Next
    INDEX
    Explanations

    wid

    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
    rible
    -1.02
     متعلقه
    -0.90
    parsedMessage
    -0.90
    :✨
    -0.89
     propOrder
    -0.84
    Geplaatst
    -0.80
    expandindo
    -0.79
     referenties
    -0.78
    HomeAsUpEnabled
    -0.77
     NSCoder
    -0.75
    POSITIVE LOGITS
     Kit
    0.45
     Serving
    0.45
    ાય
    0.45
    heme
    0.42
     گیر
    0.41
    hafter
    0.41
     köt
    0.40
    })));
    0.40
    ince
    0.40
    od
    0.40
    Activations Density 1.619%

    No Known Activations