© 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. 92959
    Prev
    Next
    INDEX
    Explanations

    gallery, patterns

    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
    Patterns
    -0.78
     Patterns
    -0.66
     toss
    -0.48
    ed
    -0.47
    ță
    -0.42
     passage
    -0.41
    ilim
    -0.40
    er
    -0.40
     skip
    -0.39
    都合
    -0.39
    POSITIVE LOGITS
     ujednoznacz
    0.87
     nakalista
    0.78
    RenderAtEndOf
    0.74
     MonoBehaviour
    0.73
    findpost
    0.73
    StoreMessageInfo
    0.69
    httphttps
    0.68
     समीक्षक
    0.68
     CreateTagHelper
    0.66
    awtextra
    0.66
    Activations Density 0.236%

    No Known Activations