© 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. 39849
    Prev
    Next
    INDEX
    Explanations

    research

    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
     research
    -1.88
     Research
    -1.70
    research
    -1.59
    Research
    -1.58
     RESEARCH
    -1.44
    RESEARCH
    -1.20
     researching
    -1.13
    研究
    -1.03
     researched
    -1.02
     penelitian
    -1.02
    POSITIVE LOGITS
    monials
    0.66
     understatement
    0.63
     ExecuteAsync
    0.63
     Commencez
    0.60
    ніципа
    0.60
     виправивши
    0.60
    __':
    0.59
    yntaxException
    0.59
    seteq
    0.58
    toarele
    0.57
    Activations Density 1.346%

    No Known Activations