© 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. 1-CLT-HP
    4. 45671
    Prev
    Next
    INDEX
    Explanations

    species names

    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
    findpost
    -0.55
     beginnetje
    -0.46
    impulan
    -0.45
    ContextHolder
    -0.43
     lapangan
    -0.43
    文句
    -0.41
     T
    -0.41
    forever
    -0.41
     väli
    -0.40
    大変
    -0.40
    POSITIVE LOGITS
    windowFixed
    0.66
    Autoritní
    0.64
    HtmlAttribute
    0.60
     ddelweddau
    0.57
    fum
    0.57
    "])
    
    0.56
     Deliber
    0.56
     stihl
    0.55
     pinulongan
    0.55
    ponses
    0.54
    Activations Density 0.002%

    No Known Activations