© 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. 5-CLT-HP
    7. 91837
    Prev
    Next
    INDEX
    Explanations

    as

    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
     a
    -0.63
    Климат
    -0.56
     at
    -0.54
     the
    -0.54
    vensko
    -0.53
    hofen
    -0.51
    kasse
    -0.50
    ционно
    -0.50
     estis
    -0.49
     an
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    0.85
     يتيمه
    0.82
     betweenstory
    0.80
    SharedCtor
    0.79
    WebMethod
    0.75
    omitempty
    0.68
    contentLoaded
    0.67
     تضيفلها
    0.66
    DataAnnotations
    0.65
    Referanser
    0.63
    Activations Density 0.001%

    No Known Activations