© 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. 1-CLT-HP
    4. 479
    Prev
    Next
    INDEX
    Explanations

    engineer

    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
     didReceive
    -0.50
    esgue
    -0.46
     deed
    -0.46
    ITest
    -0.43
    matitis
    -0.43
    Scho
    -0.42
     Scho
    -0.41
    pnea
    -0.41
    rę
    -0.41
    opardy
    -0.41
    POSITIVE LOGITS
    oredCriteria
    0.78
    awtextra
    0.75
     autorytatywna
    0.75
    tvguidetime
    0.69
    ReusableCell
    0.69
    ########.
    0.69
    Geplaatst
    0.66
    OGND
    0.65
    InjectAttribute
    0.65
    MigrationBuilder
    0.65
    Activations Density 0.006%

    No Known Activations