© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 327
    Prev
    Next
    INDEX
    Explanations

    ork

    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
    ьаж
    -0.61
    endphp
    -0.56
    yntaxException
    -0.54
    تقاوى
    -0.54
    msgTypes
    -0.53
    fjspx
    -0.52
    EndGlobalSection
    -0.52
     otomatig
    -0.50
    uxxxx
    -0.50
    ifrance
    -0.50
    POSITIVE LOGITS
     cầu
    0.63
    CloseOperation
    0.54
    es
    0.53
    kesh
    0.50
    ical
    0.49
    isl
    0.49
     लेकर
    0.48
    ic
    0.48
    ńskich
    0.48
    ial
    0.47
    Activations Density 0.040%

    No Known Activations