© 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. 1-CLT-HP
    7. 328
    Prev
    Next
    INDEX
    Explanations

    with/to

    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
     respectivas
    -0.61
     exécut
    -0.59
     enfans
    -0.59
    TagMode
    -0.59
     épaules
    -0.58
     tarko
    -0.57
     másik
    -0.57
     restantes
    -0.55
     tarjo
    -0.55
     respectivos
    -0.55
    POSITIVE LOGITS
     poffible
    0.81
    ]")]
    0.77
     occaf
    0.70
     leſs
    0.69
     Efq
    0.68
     themſelves
    0.68
    ]--;
    0.66
     Jefus
    0.66
    BagLayout
    0.66
     Eſ
    0.66
    Activations Density 0.026%

    No Known Activations