© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91941
    Prev
    Next
    INDEX
    Explanations

    code/computing

    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
    annas
    -1.58
    esar
    -1.09
    ESAR
    -0.59
    anna
    -0.54
     Bergh
    -0.51
     Press
    -0.49
    ejs
    -0.48
    nių
    -0.48
     Par
    -0.48
    jsonp
    -0.47
    POSITIVE LOGITS
    =$?
    0.65
    nocache
    0.61
     teck
    0.59
    Controllo
    0.57
    BufferException
    0.57
    oubtedly
    0.56
    TargetException
    0.56
     itſelf
    0.56
    tvguidetime
    0.55
    JspWriter
    0.55
    Activations Density 0.046%

    No Known Activations