© 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. 4-CLT-HP
    7. 628
    Prev
    Next
    INDEX
    Explanations

    comparison

    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
     transférez
    -0.72
     poveznice
    -0.67
    Personensuche
    -0.63
     desks
    -0.62
    IBOutlet
    -0.62
    fhir
    -0.60
    uxxxx
    -0.60
    chability
    -0.59
    kuuta
    -0.59
     समीक्षाओं
    -0.59
    POSITIVE LOGITS
     or
    0.58
     and
    0.58
     likely
    0.50
     rather
    0.46
     difficult
    0.45
    elebr
    0.45
    complexType
    0.43
     pronon
    0.43
     affordable
    0.41
     complex
    0.40
    Activations Density 0.002%

    No Known Activations