© 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. 44092
    Prev
    Next
    INDEX
    Explanations

    enantiomers

    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
     Monfieur
    -0.89
     Houſe
    -0.87
     Reſ
    -0.80
     Jefus
    -0.76
     Eſ
    -0.73
     Efq
    -0.72
     purpoſe
    -0.71
     Diſ
    -0.70
     Anſ
    -0.70
    XmlEnum
    -0.69
    POSITIVE LOGITS
    s
    1.63
    t
    0.96
    a
    0.95
    ی
    0.93
    n
    0.80
    sing
    0.76
    sand
    0.75
    en
    0.75
    ses
    0.74
    san
    0.74
    Activations Density 0.078%

    No Known Activations