© 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. 1-CLT-HP
    7. 13669
    Prev
    Next
    INDEX
    Explanations

    much

    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
    Примечания
    -0.54
     समीक्षाओं
    -0.44
     lunga
    -0.41
    Dau
    -0.41
    WithMany
    -0.40
    Ascending
    -0.39
    räumen
    -0.39
    InteropServices
    -0.38
     pinulongan
    -0.38
     boty
    -0.38
    POSITIVE LOGITS
    fromCharCode
    0.72
     Administrativna
    0.70
    andoah
    0.65
     wetter
    0.64
    Largura
    0.62
     bigger
    0.61
     Tequila
    0.60
    DockStyle
    0.60
    DECREF
    0.60
    SPATH
    0.60
    Activations Density 0.008%

    No Known Activations