© 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. 44120
    Prev
    Next
    INDEX
    Explanations

    Saw/Sawyer

    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
     Saw
    -1.29
    Saw
    -1.09
    SAW
    -0.91
     Sawyer
    -0.91
     SAW
    -0.91
    BeginContext
    -0.60
     OnInit
    -0.58
     beginnetje
    -0.58
    saw
    -0.57
    abestanden
    -0.57
    POSITIVE LOGITS
     Jefus
    0.57
     Theſe
    0.53
     geox
    0.50
    gether
    0.49
    Puck
    0.49
     rispar
    0.48
    ardless
    0.48
    quele
    0.47
    wezig
    0.47
     corris
    0.46
    Activations Density 0.128%

    No Known Activations