© 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. 0-CLT-HP
    7. 41797
    Prev
    Next
    INDEX
    Explanations

    origins or limits

    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
     condamné
    -0.59
    élimin
    -0.57
    ruimte
    -0.56
    chyma
    -0.56
    équi
    -0.55
     őket
    -0.54
    habitude
    -0.54
    ">//
    -0.54
    dollis
    -0.53
     kaarangay
    -0.52
    POSITIVE LOGITS
    ImageContext
    0.63
     personal
    0.55
     ModelExpression
    0.52
     number
    0.50
     PERSONAL
    0.48
     person
    0.48
     pair
    0.46
     persons
    0.46
    RegistryLite
    0.46
    ListItemIcon
    0.46
    Activations Density 0.082%

    No Known Activations