© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2440
    Prev
    Next
    INDEX
    Explanations

    of

    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
     مشين
    -0.73
    VIAF
    -0.71
    rungsseite
    -0.69
    AccessorTable
    -0.67
    buttonBar
    -0.66
     виправивши
    -0.66
    Atsauces
    -0.66
     мәкал
    -0.65
     فريبيس
    -0.65
     fathoms
    -0.61
    POSITIVE LOGITS
    unce
    0.54
    ism
    0.53
    ione
    0.50
     facto
    0.47
    ist
    0.47
    antd
    0.47
     wis
    0.47
     fact
    0.45
    ists
    0.45
    참고
    0.44
    Activations Density 0.028%

    No Known Activations