© 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. 1541
    Prev
    Next
    INDEX
    Explanations

    film or thin layers

    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
     AssemblyCulture
    -0.76
    WebElementEntity
    -0.69
    rungsseite
    -0.63
    下载附件
    -0.60
    Pageable
    -0.59
    
    -0.59
    ⓧ
    -0.59
    Rote
    -0.57
    ContentAsync
    -0.53
    ":[{
    -0.53
    POSITIVE LOGITS
    nlm
    0.57
     universitarios
    0.52
    umman
    0.50
    ty
    0.50
     poveznice
    0.50
     of
    0.49
     particuliers
    0.49
    adomo
    0.49
     laissé
    0.48
    parsedMessage
    0.47
    Activations Density 0.016%

    No Known Activations