© 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. 71994
    Prev
    Next
    INDEX
    Explanations

    technical documents and code

    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
    ScopeManager
    -0.86
     الحره
    -0.82
    NewUrlParser
    -0.78
     المعيارى
    -0.75
     jScrollPane
    -0.72
     Chwiliwch
    -0.72
     كومونز
    -0.71
     Meksiku
    -0.71
    RegistryLite
    -0.68
    RegressionTest
    -0.65
    POSITIVE LOGITS
     pl
    0.60
     hazard
    0.50
     conditioned
    0.49
    conditioned
    0.46
     occupied
    0.43
     fa
    0.42
    zula
    0.42
     work
    0.42
     IT
    0.41
    lli
    0.41
    Activations Density 0.000%

    No Known Activations