© 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. 737
    Prev
    Next
    INDEX
    Explanations

    3

    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
    abar
    -0.48
    Eloquent
    -0.45
     inves
    -0.45
    ਼
    -0.43
     IBOutlet
    -0.43
    lucene
    -0.42
     nr
    -0.42
    kari
    -0.41
    lax
    -0.41
    ios
    -0.41
    POSITIVE LOGITS
     ddelweddau
    0.77
    XmlAccessType
    0.65
    municipi
    0.62
    Ссылки
    0.60
     disponibilités
    0.59
     myſelf
    0.57
    ConstraintMaker
    0.57
    வர்
    0.56
    fony
    0.56
    createObject
    0.56
    Activations Density 0.002%

    No Known Activations