© 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. 44195
    Prev
    Next
    INDEX
    Explanations

    theory and experiment

    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
     theory
    -0.68
     Theory
    -0.66
     الرياضيه
    -0.66
    Theory
    -0.57
    theory
    -0.55
     THEORY
    -0.55
    ">//
    -0.54
    ResumeLayout
    -0.51
     الحره
    -0.51
     тео
    -0.50
    POSITIVE LOGITS
    identiality
    0.65
    felf
    0.59
     Jefus
    0.58
    gsub
    0.57
    картинка
    0.57
     pleaſure
    0.56
    isdigit
    0.56
     varandra
    0.52
     pngtree
    0.52
     crdi
    0.52
    Activations Density 0.068%

    No Known Activations