© 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. 5-CLT-HP
    7. 1094
    Prev
    Next
    INDEX
    Explanations

    focus

    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
    ôtel
    -0.63
    fromnode
    -0.60
     محفوظة
    -0.59
     Exacts
    -0.59
    webElement
    -0.58
     createSprite
    -0.58
     Wiktionnaire
    -0.58
    rower
    -0.57
    ]--;
    -0.57
    ringing
    -0.56
    POSITIVE LOGITS
     is
    0.66
     drifts
    0.61
     returns
    0.54
     retorna
    0.48
     مشارکت‌کنندگان
    0.47
     happens
    0.47
     settles
    0.47
     wan
    0.47
     remains
    0.47
     needs
    0.46
    Activations Density 0.001%

    No Known Activations