© 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. 12137
    Prev
    Next
    INDEX
    Explanations

    formal publications

    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
    lick
    -0.92
    bate
    -0.70
     lick
    -0.60
    sities
    -0.54
     licks
    -0.54
    EDEFAULT
    -0.52
    NewGuid
    -0.51
    ját
    -0.49
     Scratch
    -0.48
     Cull
    -0.47
    POSITIVE LOGITS
    TagMode
    0.87
     дописавши
    0.83
    :✨
    0.69
    titleMargin
    0.66
    riwal
    0.64
     Италијани
    0.63
     cherchés
    0.62
    principalTable
    0.60
    Brainz
    0.59
     Wiktionnaire
    0.58
    Activations Density 0.043%

    No Known Activations