© 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. 0-CLT-HP
    7. 93353
    Prev
    Next
    INDEX
    Explanations

    syndromes

    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
     AssemblyCulture
    -1.01
    SharedDtor
    -0.87
     defaultstate
    -0.82
    posedge
    -0.81
    Hentet
    -0.78
    ArgsConstructor
    -0.77
     démocratie
    -0.77
    الحياه
    -0.74
    PyExc
    -0.73
     незавершена
    -0.73
    POSITIVE LOGITS
    amik
    0.49
     Covered
    0.45
    sqcup
    0.45
    eridge
    0.43
    alini
    0.43
     SUBST
    0.43
    Covered
    0.42
     surrogate
    0.41
     Terrain
    0.40
    atera
    0.40
    Activations Density 0.142%

    No Known Activations