© 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. 5-CLT-HP
    7. 3462
    Prev
    Next
    INDEX
    Explanations

    Formal/technical writing

    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
    rungsseite
    -0.92
    MigrationBuilder
    -0.83
     Мексичка
    -0.81
    ьаж
    -0.80
     חיצוניים
    -0.72
    __':
    -0.71
    writeField
    -0.69
     has
    -0.66
    riwal
    -0.66
     BoxFit
    -0.65
    POSITIVE LOGITS
     considering
    0.53
     working
    0.49
     assuming
    0.45
     macroscopic
    0.44
     waiting
    0.43
    stwie
    0.43
     realizing
    0.43
    retz
    0.42
     clicking
    0.42
    richtig
    0.41
    Activations Density 0.001%

    No Known Activations