© 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. 5-CLT-HP
    7. 92187
    Prev
    Next
    INDEX
    Explanations

    put

    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
    criture
    -0.46
     piele
    -0.46
     yön
    -0.42
    ustainable
    -0.42
    ennung
    -0.42
     piú
    -0.41
     arquitecto
    -0.40
     originais
    -0.40
    fetchone
    -0.40
    ennia
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    0.75
    Rptr
    0.72
     disambiguazione
    0.69
    HasAnnotation
    0.68
    SpringBootTest
    0.68
     يتيمه
    0.67
    enderror
    0.65
    بوابة
    0.64
    PerformLayout
    0.63
    دانشنامهٔ
    0.63
    Activations Density 0.041%

    No Known Activations