© 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. 41979
    Prev
    Next
    INDEX
    Explanations

    malignant

    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
     withstand
    -0.77
    unknownFields
    -0.77
     Савезне
    -0.75
     <<<<<<<<<<<<<<
    -0.66
    SerializedName
    -0.63
    الإنجليزية
    -0.62
    Tē
    -0.62
     dAtA
    -0.61
    verwijspagina
    -0.61
     synag
    -0.61
    POSITIVE LOGITS
    ing
    0.99
    s
    0.88
    ting
    0.74
    ments
    0.72
    ment
    0.70
    ness
    0.69
    ring
    0.69
    ging
    0.64
    ry
    0.63
    IMENTS
    0.63
    Activations Density 1.038%

    No Known Activations