© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78076
    Prev
    Next
    INDEX
    Explanations

    Wid

    np_max-act-logits · 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
    Negative Logits
    Personendaten
    -0.77
    сылкі
    -0.76
    IndentedString
    -0.71
    InputBorder
    -0.71
    RegistryLite
    -0.68
    AsUp
    -0.66
     jScrollPane
    -0.66
     NSCoder
    -0.65
     betweenstory
    -0.65
     snippetHide
    -0.64
    POSITIVE LOGITS
    owed
    0.66
    ow
    0.55
    ower
    0.53
    OWER
    0.48
    ows
    0.48
    si
    0.46
    enfance
    0.45
    OW
    0.44
     owed
    0.43
     owe
    0.43
    Activations Density 0.002%

    No Known Activations