Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 632
    Prev
    Next
    INDEX
    Explanations

    venom

    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
    Hochspringen
    -1.00
     contextLoads
    -0.84
     ujednoznacz
    -0.82
     مرئيه
    -0.81
    GEBURTSDATUM
    -0.81
    ]--;
    -0.79
    OrNil
    -0.79
    存于互联网档案馆
    -0.76
    IndentedString
    -0.73
     HttpNotFound
    -0.73
    POSITIVE LOGITS
    s
    0.76
     origini
    0.50
     to
    0.49
     Messrs
    0.47
    ház
    0.47
     домой
    0.45
    www
    0.43
    ся
    0.43
    ات
    0.43
    shy
    0.42
    Activations Density 0.033%

    No Known Activations