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. 91609
    Prev
    Next
    INDEX
    Explanations

    punctuation/formatting characters

    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
    TagMode
    -0.59
     thank
    -0.58
     "..\..\..\
    -0.58
     this
    -0.56
    mately
    -0.56
     closely
    -0.55
     conditions
    -0.54
     <<<<<<<<<<<<<<
    -0.54
     anot
    -0.54
     ordinary
    -0.54
    POSITIVE LOGITS
    <bos>
    0.77
    )”
    0.76
    ThroughAttribute
    0.72
    ),”
    0.68
    ”)
    0.60
    ”
    0.58
    )”.
    0.57
     AssemblyCompany
    0.56
    ).”
    0.56
    ”]
    0.54
    Activations Density 0.034%

    No Known Activations