© 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. 5-CLT-HP
    7. 896
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    NameInMap
    -0.69
     يتيمه
    -0.69
     decorativo
    -0.59
     Pind
    -0.56
    jména
    -0.55
    strconv
    -0.54
     Paglinawan
    -0.54
    ondissement
    -0.52
     '\\;'
    -0.50
     skull
    -0.50
    POSITIVE LOGITS
    lase
    0.65
    AndEndTag
    0.61
    TestBed
    0.53
    ylase
    0.50
    الحياه
    0.49
    liferay
    0.47
    lation
    0.47
    per
    0.47
    ContentAsync
    0.46
    las
    0.45
    Activations Density 0.004%

    No Known Activations