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. 1-CLT-HP
    4. 12851
    Prev
    Next
    INDEX
    Explanations

    distance measurement

    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
     postIndex
    -0.73
     invokingState
    -0.70
     defaultstate
    -0.69
    يميديا
    -0.67
    SourceChecksum
    -0.67
    CppMethod
    -0.66
    @[+][
    -0.66
    matchCondition
    -0.66
    IntoConstraints
    -0.65
    InsertCommand
    -0.65
    POSITIVE LOGITS
    Ecotoxicity
    0.47
    Xamarin
    0.43
     IDisposable
    0.42
    IntentFilter
    0.42
    qxd
    0.41
    AppBar
    0.39
     realiz
    0.37
     there
    0.37
    horesis
    0.36
    ,:),
    0.36
    Activations Density 0.030%

    No Known Activations