© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40225
    Prev
    Next
    INDEX
    Explanations

    blog posts/articles

    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
    tingly
    -1.84
     swan
    -0.74
    providedIn
    -0.74
    alyptus
    -0.73
    Personensuche
    -0.66
    GEBURTSDATUM
    -0.64
     autrefois
    -0.60
    makeConstraints
    -0.60
    atalyst
    -0.60
     volon
    -0.60
    POSITIVE LOGITS
     AssemblyVersion
    0.44
     recapture
    0.44
    izza
    0.43
     wezen
    0.43
    Initializable
    0.42
    Tril
    0.41
     мәкал
    0.41
    ẳng
    0.41
    siehe
    0.40
     ويكيميديا
    0.40
    Activations Density 1.664%

    No Known Activations