© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13024
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
     ferry
    -1.32
     Ferry
    -1.23
     ferries
    -1.17
    Ferry
    -1.01
    ferry
    -0.86
    ing
    -0.50
    piro
    -0.46
    énez
    -0.45
    おり
    -0.45
    ERSHIP
    -0.44
    POSITIVE LOGITS
     Efq
    1.03
     itſelf
    0.98
     pleaſure
    0.93
     Jefus
    0.93
     ſche
    0.91
     purpoſe
    0.90
     faſt
    0.89
     myſelf
    0.89
     iſt
    0.84
     Reſ
    0.82
    Activations Density 0.017%

    No Known Activations