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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38318
    Prev
    Next
    INDEX
    Explanations

    Contact

    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
     bizony
    -0.45
     tider
    -0.43
     centaines
    -0.42
     Contact
    -0.42
    Contact
    -0.40
     milliers
    -0.39
     pattes
    -0.38
    Register
    -0.37
    fourths
    -0.36
     fundamentos
    -0.36
    POSITIVE LOGITS
    ing
    1.78
    ING
    1.16
     незавершена
    0.83
    ed
    0.83
    extAlignment
    0.81
    ytale
    0.81
    GOTREF
    0.78
    ableness
    0.78
    ingl
    0.75
    orious
    0.73
    Activations Density 0.147%

    No Known Activations