Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74577
    Prev
    Next
    INDEX
    Explanations

    Technical/Programming content

    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
    olymer
    -0.50
    AnchorStyles
    -0.47
    liferay
    -0.45
    JoinTable
    -0.44
    ldt
    -0.44
    ortment
    -0.44
    XMLSchema
    -0.43
    GraphicsUnit
    -0.43
     PT
    -0.42
     addSubview
    -0.42
    POSITIVE LOGITS
    titleMargin
    0.75
    WithIOException
    0.66
     ModelExpression
    0.63
     disambiguazione
    0.63
     ProtoMessage
    0.60
     OMITBAD
    0.59
    AsUp
    0.59
    ArrowToggle
    0.59
    INSEE
    0.56
    FormTagHelper
    0.56
    Activations Density 0.001%

    No Known Activations