Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40846
    Prev
    Next
    INDEX
    Explanations

    exempt

    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
     pey
    -0.68
    GraphicsUnit
    -0.66
     мәкалә
    -0.66
    waitKey
    -0.66
     juſ
    -0.66
    lectric
    -0.63
    exempt
    -0.63
     Roskov
    -0.62
     EdgeInsets
    -0.62
     Conn
    -0.62
    POSITIVE LOGITS
    ysing
    0.59
    ening
    0.48
     ch
    0.47
    teto
    0.47
    WebServlet
    0.46
     v
    0.45
    ingly
    0.44
    ciato
    0.42
    oriasis
    0.42
    erstein
    0.42
    Activations Density 0.124%

    No Known Activations