© 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. 13772
    Prev
    Next
    INDEX
    Explanations

    next

    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
     незавершена
    -0.73
     next
    -0.68
     صوتيه
    -0.66
     AssemblyCulture
    -0.66
     <<<<<<<<<<<<<<
    -0.64
     coté
    -0.61
     prossima
    -0.60
    ciutto
    -0.60
    CloseOperation
    -0.59
    Jeografia
    -0.59
    POSITIVE LOGITS
     CBA
    0.49
     round
    0.49
     TVA
    0.46
    zhen
    0.44
    wpi
    0.44
    MigrationBuilder
    0.43
    utives
    0.42
    round
    0.42
     BART
    0.41
     BIA
    0.41
    Activations Density 0.014%

    No Known Activations