© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10194
    Prev
    Next
    INDEX
    Explanations

    critical reviews

    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
     EconPapers
    -0.82
     مرئيه
    -0.78
     disambiguazione
    -0.78
    contentLoaded
    -0.78
    utilisons
    -0.76
     typelib
    -0.76
     المعيارى
    -0.76
     critical
    -0.74
     Audiodateien
    -0.73
    ſelves
    -0.68
    POSITIVE LOGITS
     leg
    0.50
     cam
    0.47
    терак
    0.45
    тю
    0.44
    laise
    0.43
     et
    0.43
    timestamps
    0.42
     shoes
    0.42
     incidents
    0.41
     Incident
    0.41
    Activations Density 0.004%

    No Known Activations