Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91876
    Prev
    Next
    INDEX
    Explanations

    During

    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
    After
    -0.78
     Anſ
    -0.72
    Before
    -0.69
     faſt
    -0.68
     Houſe
    -0.67
     Monfieur
    -0.66
    During
    -0.66
     Diſ
    -0.66
    Within
    -0.64
     Reſ
    -0.63
    POSITIVE LOGITS
     the
    1.49
     his
    1.07
     a
    0.99
     their
    0.95
     her
    0.91
     this
    0.91
    ward
    0.88
     an
    0.87
     your
    0.87
     our
    0.85
    Activations Density 0.054%

    No Known Activations