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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40190
    Prev
    Next
    INDEX
    Explanations

    measurements and concentrations

    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
     noticed
    -0.80
    noticed
    -0.71
    MigrationBuilder
    -0.69
     noticeable
    -0.69
    bond
    -0.68
    eramente
    -0.67
     bonds
    -0.66
    zers
    -0.66
    %]
    -0.65
    Unusual
    -0.65
    POSITIVE LOGITS
    s
    0.65
     onPostExecute
    0.58
     externi
    0.47
    WebElementEntity
    0.45
    ToScroll
    0.41
    MethodManager
    0.39
    oi
    0.37
    omed
    0.37
    lıyor
    0.37
    ly
    0.37
    Activations Density 0.043%

    No Known Activations