© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 14838
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    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
     marten
    -1.37
     martens
    -1.00
     Marten
    -0.90
     Martens
    -0.67
    隼
    -0.41
     före
    -0.40
    ATT
    -0.38
    Slf
    -0.37
    alth
    -0.37
    readAs
    -0.36
    POSITIVE LOGITS
    发表于
    0.77
    abestanden
    0.77
    Filmographie
    0.76
     doInBackground
    0.75
    ergies
    0.73
    /**
    0.68
     nhàng
    0.68
    eing
    0.68
    cinfo
    0.64
    /*
    0.63
    Activations Density 0.013%

    No Known Activations