© 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. 20-CLT-HP
    7. 75324
    Prev
    Next
    INDEX
    Explanations

    for

    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
     Developed
    -1.16
    Developed
    -1.07
    developed
    -1.06
     Created
    -1.05
    Created
    -0.96
     developed
    -0.95
     Launched
    -0.94
    Constructed
    -0.94
     Built
    -0.93
    InjectAttribute
    -0.90
    POSITIVE LOGITS
    timeScale
    0.49
     the
    0.38
    angan
    0.33
    árs
    0.30
    ê
    0.30
    UserData
    0.29
    EntityType
    0.29
     паро
    0.29
    FieldValue
    0.29
     mot
    0.28
    Activations Density 0.000%

    No Known Activations