© 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. 45147
    Prev
    Next
    INDEX
    Explanations

    vulgaris

    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
     moles
    -0.91
    RegressionTest
    -0.80
     mole
    -0.79
    contentLoaded
    -0.77
     Moles
    -0.70
     Generals
    -0.67
     vulgaris
    -0.65
    хьтан
    -0.65
    moles
    -0.65
    TargetException
    -0.65
    POSITIVE LOGITS
    a
    0.63
    ian
    0.60
    i
    0.59
    imeter
    0.54
    enumii
    0.52
     inflater
    0.52
    nologies
    0.51
    maiden
    0.50
    istan
    0.49
    󠁴
    0.48
    Activations Density 1.407%

    No Known Activations