© 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. 91975
    Prev
    Next
    INDEX
    Explanations

    those

    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
     those
    -2.61
    those
    -2.41
    Those
    -2.27
     Those
    -2.11
     THOSE
    -1.86
     ceux
    -1.67
     quelli
    -1.53
     aqueles
    -1.53
     thoſe
    -1.48
     aquellos
    -1.43
    POSITIVE LOGITS
    ScopeManager
    0.93
    __':
    0.70
    __":
    0.70
    RegressionTest
    0.69
    EnableWeb
    0.67
     betweenstory
    0.66
     days
    0.66
    rungsseite
    0.65
     kinds
    0.63
     '\\;'
    0.63
    Activations Density 0.034%

    No Known Activations