© 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. 0-CLT-HP
    7. 45207
    Prev
    Next
    INDEX
    Explanations

    code

    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
     autorytatywna
    -1.10
     they
    -1.03
    their
    -1.01
     their
    -0.96
    they
    -0.93
    Mereka
    -0.89
     eorum
    -0.88
     Shakspeare
    -0.88
     Họ
    -0.87
     auffi
    -0.85
    POSITIVE LOGITS
     
    0.69
     don
    0.65
    ’
    0.60
     c
    0.58
     De
    0.57
     U
    0.56
     (
    0.56
     got
    0.55
     o
    0.54
     s
    0.52
    Activations Density 0.128%

    No Known Activations