© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3281
    Prev
    Next
    INDEX
    Explanations

    data

    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
     transfieras
    -0.60
    writeFieldEnd
    -0.58
    ipedi
    -0.55
     disambiguazione
    -0.54
     CURIAM
    -0.51
    SBATCH
    -0.49
     дописавши
    -0.49
    хьтан
    -0.48
    İstinadlar
    -0.48
    Manbalar
    -0.47
    POSITIVE LOGITS
     are
    1.29
     were
    0.92
     aren
    0.83
     have
    0.80
     indicate
    0.72
     ARE
    0.71
     contain
    0.70
     come
    0.69
     reflect
    0.68
    Are
    0.67
    Activations Density 0.008%

    No Known Activations