© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45099
    Prev
    Next
    INDEX
    Explanations

    body

    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
     חיצוניים
    -0.59
    bindParam
    -0.50
     ddelweddau
    -0.48
    ########.
    -0.44
     millón
    -0.44
     号
    -0.43
    릿
    -0.43
    APH
    -0.42
     externi
    -0.42
    unately
    -0.41
    POSITIVE LOGITS
    '
    0.93
    ’
    0.89
    IUrlHelper
    0.74
    <bos>
    0.73
     wireType
    0.66
     world
    0.65
     initComponents
    0.64
    UnknownFields
    0.63
    RuleContext
    0.62
    \'
    0.61
    Activations Density 0.113%

    No Known Activations