© 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. 968
    Prev
    Next
    INDEX
    Explanations

    medical/technical descriptions

    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
    awtextra
    -0.67
    lapsingToolbar
    -0.66
     Италијани
    -0.65
     esternos
    -0.63
     iprot
    -0.62
     disambiguazione
    -0.60
    AndroidJUnit
    -0.59
     SwitchCompat
    -0.58
    ]};
    -0.57
     jScrollPane
    -0.56
    POSITIVE LOGITS
     تانيه
    0.57
    出版年
    0.52
    Билгалдахарш
    0.48
    usis
    0.48
     faveur
    0.46
    पया
    0.45
     improving
    0.44
     improvement
    0.42
    tuu
    0.42
    сиона
    0.41
    Activations Density 0.003%

    No Known Activations