© 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. 4-CLT-HP
    7. 4353
    Prev
    Next
    INDEX
    Explanations

    ADHD

    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
    -0.73
    存于互联网档案馆
    -0.64
    
    -0.63
    iforms
    -0.58
     varargin
    -0.57
    utilisons
    -0.55
    ölkerung
    -0.54
     loam
    -0.53
    forests
    -0.53
     consultato
    -0.52
    POSITIVE LOGITS
    iela
    0.56
    iel
    0.54
    ifel
    0.50
    quiel
    0.49
     Qué
    0.48
    esterno
    0.45
    Portály
    0.44
    quela
    0.44
    peek
    0.44
     compéti
    0.43
    Activations Density 0.003%

    No Known Activations