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. 44790
    Prev
    Next
    INDEX
    Explanations

    windows and editors

    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
    Diwedd
    -0.75
    HasForeignKey
    -0.74
     purpoſe
    -0.74
    MLLoader
    -0.72
     Viewer
    -0.71
     myſelf
    -0.71
     pleaſure
    -0.69
     ſtate
    -0.68
     Majefty
    -0.68
     uſe
    -0.68
    POSITIVE LOGITS
     and
    0.50
     for
    0.49
    ONAUT
    0.46
     dom
    0.45
    quelize
    0.45
     from
    0.45
     with
    0.44
     ($
    0.43
     --
    0.42
     by
    0.42
    Activations Density 0.383%

    No Known Activations