© 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. 20-CLT-HP
    7. 76809
    Prev
    Next
    INDEX
    Explanations

    code and web addresses

    np_max-act-logits · 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
    Życiorys
    -0.65
     AssemblyCompany
    -0.63
    WebElementEntity
    -0.60
    textTheme
    -0.56
    Rhestr
    -0.56
    Personendaten
    -0.55
     lượt
    -0.53
    BeginContext
    -0.51
    ########.
    -0.51
     Serializer
    -0.50
    POSITIVE LOGITS
    nonatomic
    0.56
    abatic
    0.52
     Fl
    0.52
     fl
    0.50
     South
    0.50
    fl
    0.49
    Vla
    0.47
     GORDON
    0.46
     Gama
    0.46
    Fl
    0.45
    Activations Density 0.003%

    No Known Activations