© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38773
    Prev
    Next
    INDEX
    Explanations

    Test

    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
    Test
    -0.58
     clearance
    -0.48
    nya
    -0.42
    JOptionPane
    -0.42
    وسف
    -0.42
    imenti
    -0.41
    ómicas
    -0.41
    ificato
    -0.40
    ser
    -0.40
     endfor
    -0.39
    POSITIVE LOGITS
    PhysRevD
    0.75
     Италијани
    0.75
    ftagPool
    0.74
    windowFixed
    0.71
    RegressionTest
    0.70
     متعلقه
    0.69
    ratislava
    0.69
    хьтан
    0.67
    ỡng
    0.65
     disambiguazione
    0.65
    Activations Density 0.083%

    No Known Activations