© 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. 12475
    Prev
    Next
    INDEX
    Explanations

    job descriptions

    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
    atum
    -0.86
     Cory
    -0.62
    atus
    -0.59
    ATUM
    -0.59
    Cory
    -0.53
    stand
    -0.52
    catus
    -0.52
    geld
    -0.51
     trạng
    -0.50
    (&:
    -0.49
    POSITIVE LOGITS
     فريبيس
    1.00
    aarrggbb
    0.88
     EconPapers
    0.81
    AndEndTag
    0.80
     мәкал
    0.78
     незавершена
    0.76
    EndContext
    0.74
    setVerticalGroup
    0.74
    +#+
    0.73
    Jeografia
    0.70
    Activations Density 0.060%

    No Known Activations