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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73981
    Prev
    Next
    INDEX
    Explanations

    hacking, making

    np_max-act-logits · 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
    EDEFAULT
    -0.65
    ModelSerializer
    -0.63
    (!__
    -0.56
    MockMvc
    -0.56
    نج
    -0.55
    MessageOf
    -0.52
    otene
    -0.50
    familien
    -0.50
    enaire
    -0.48
    出版年
    -0.48
    POSITIVE LOGITS
     hack
    0.60
     hackers
    0.60
     Hack
    0.58
     slam
    0.54
     uncon
    0.54
     makers
    0.54
     meet
    0.53
    makers
    0.52
     colle
    0.52
     maker
    0.51
    Activations Density 0.000%

    No Known Activations