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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1321
    Prev
    Next
    INDEX
    Explanations

    working

    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
     '\\;'
    -0.61
    VolleyError
    -0.59
    jsonwebtoken
    -0.59
    EndProject
    -0.59
    intios
    -0.57
    RTSN
    -0.56
    twimg
    -0.56
    脚注の使い方
    -0.55
    encodeWith
    -0.55
    FTFY
    -0.54
    POSITIVE LOGITS
    TagMode
    0.57
     country
    0.55
    reathable
    0.54
    chyma
    0.51
     prolet
    0.50
    asmuch
    0.48
     Country
    0.46
    mless
    0.44
    ware
    0.44
    colage
    0.44
    Activations Density 0.001%

    No Known Activations