© 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. 5-CLT-HP
    7. 97197
    Prev
    Next
    INDEX
    Explanations

    -

    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
     nakalista
    -0.95
    abestanden
    -0.85
     Roskov
    -0.83
    osoba
    -0.66
    SqlSession
    -0.65
     DbSet
    -0.62
     resourceCulture
    -0.62
     CascadeType
    -0.61
    ConstraintMaker
    -0.60
     typelib
    -0.59
    POSITIVE LOGITS
     generated
    0.49
    setViewportView
    0.49
     from
    0.49
     vector
    0.45
     vectors
    0.45
    來源
    0.44
     produced
    0.42
     kræ
    0.42
     forces
    0.41
     provided
    0.41
    Activations Density 0.003%

    No Known Activations