© 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. 1006
    Prev
    Next
    INDEX
    Explanations

    Walters

    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
    ilius
    -0.78
    oun
    -0.69
    aid
    -0.63
     so
    -0.62
    .
    -0.58
    <eos>
    -0.57
    a
    -0.55
     
    -0.54
    ,
    -0.54
     said
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    1.34
    ]--;
    1.12
     تضيفلها
    1.09
    Portály
    1.05
     myſelf
    1.04
     виправивши
    1.02
     iſt
    1.02
    Sucesor
    1.01
    ⓧ
    1.00
    AutoScaleMode
    1.00
    Activations Density 1.009%

    No Known Activations