© 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. 77348
    Prev
    Next
    INDEX
    Explanations

    Medical, data, programming contexts

    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
     pubblici
    -0.73
     sereia
    -0.73
     elettrico
    -0.72
    seamnă
    -0.72
     étoit
    -0.71
     rempliss
    -0.69
     rivière
    -0.69
     auroit
    -0.68
     avoient
    -0.66
     pauvres
    -0.65
    POSITIVE LOGITS
     care
    0.71
    InstrumentedTest
    0.56
     BoxDecoration
    0.54
    BeginContext
    0.45
     Care
    0.43
     InputDecoration
    0.43
     createSlice
    0.42
    WriteAttribute
    0.41
     appris
    0.40
     patin
    0.40
    Activations Density 0.001%

    No Known Activations