© 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. 39978
    Prev
    Next
    INDEX
    Explanations

    visibility

    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
     initComponents
    -0.81
     verborgen
    -0.72
    ArrowToggle
    -0.71
     visible
    -0.69
     hidden
    -0.64
     vermelhas
    -0.60
     visibilité
    -0.58
     tucked
    -0.58
     espagne
    -0.57
     desaparecido
    -0.57
    POSITIVE LOGITS
    TagMode
    0.64
    MIDDLEWARE
    0.57
    ness
    0.54
    saraba
    0.53
    ovsk
    0.52
     works
    0.52
    osoba
    0.50
    تأ
    0.50
    ist
    0.49
     record
    0.49
    Activations Density 0.025%

    No Known Activations