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. 20-CLT-HP
    4. 73905
    Prev
    Next
    INDEX
    Explanations

    small words

    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
     lenker
    -0.87
    mybatisplus
    -0.73
     '\\;'
    -0.63
     fubject
    -0.62
    Hentet
    -0.59
     Perfon
    -0.59
     nahilalakip
    -0.59
     VIDEOTAPE
    -0.59
    /*
    -0.59
    脚注の使い方
    -0.58
    POSITIVE LOGITS
     of
    0.59
     Un
    0.56
     like
    0.52
     un
    0.52
     such
    0.51
    uncher
    0.50
     –
    0.50
     -
    0.49
    like
    0.49
     in
    0.49
    Activations Density 0.005%

    No Known Activations