© 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. 4-CLT-HP
    7. 1473
    Prev
    Next
    INDEX
    Explanations

    toward/towards

    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
     using
    -0.48
     taking
    -0.45
     carrying
    -0.45
     enter
    -0.43
     not
    -0.43
     enabling
    -0.42
     bringing
    -0.42
     just
    -0.41
     pausing
    -0.40
     making
    -0.40
    POSITIVE LOGITS
     HasFactory
    0.74
    GEBURTS
    0.71
    Personensuche
    0.70
    RenderAtEndOf
    0.70
    matchCondition
    0.68
     CreateTagHelper
    0.67
     فريبيس
    0.67
    setVerticalGroup
    0.66
    awtextra
    0.66
     المعيارى
    0.63
    Activations Density 0.008%

    No Known Activations