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. 1-CLT-HP
    4. 12545
    Prev
    Next
    INDEX
    Explanations

    Code/Technical language

    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
    isata
    -0.44
    iksa
    -0.44
    部
    -0.42
    ISD
    -0.40
     द
    -0.40
    .
    -0.40
    Tē
    -0.39
    ジン
    -0.38
    ственность
    -0.38
    flot
    -0.38
    POSITIVE LOGITS
    ſelves
    0.93
     Monfieur
    0.86
     Jefus
    0.85
     myſelf
    0.82
     Theſe
    0.82
     Efq
    0.81
     purpoſe
    0.80
    ſelf
    0.80
     becauſe
    0.79
     houſe
    0.76
    Activations Density 0.019%

    No Known Activations