© 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. 4-CLT-HP
    7. 1970
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .
    -0.60
    age
    -0.44
     most
    -0.43
    kelt
    -0.41
     bedingt
    -0.40
     may
    -0.40
     has
    -0.40
     begitu
    -0.39
     is
    -0.39
     so
    -0.39
    POSITIVE LOGITS
    DockStyle
    0.82
     perpetuity
    0.80
    UpInside
    0.78
    makeConstraints
    0.71
    RegistryLite
    0.71
    URIComponent
    0.68
     للمعارف
    0.66
    хьтан
    0.66
    
    0.65
    SafeMath
    0.63
    Activations Density 0.001%

    No Known Activations