© 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. 5-CLT-HP
    7. 93395
    Prev
    Next
    INDEX
    Explanations

    silk

    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
    xtext
    -0.63
     ddelweddau
    -0.55
    protoimpl
    -0.55
     Administrativna
    -0.55
     Cæsar
    -0.54
    naeus
    -0.54
    resar
    -0.52
    brat
    -0.51
     prawn
    -0.51
    zwi
    -0.50
    POSITIVE LOGITS
    ence
    0.62
    rungsseite
    0.52
     fieldNum
    0.51
     StatefulWidget
    0.50
    ential
    0.49
    км
    0.48
     مرئيه
    0.47
    yelidikan
    0.47
    +#+#
    0.46
    enka
    0.46
    Activations Density 0.001%

    No Known Activations