© 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. 1-CLT-HP
    7. 8913
    Prev
    Next
    INDEX
    Explanations

    names/name fields

    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
     combing
    -0.65
     jenner
    -0.61
     الحره
    -0.55
     combed
    -0.55
    ứt
    -0.54
    ,:]
    -0.54
     }}$}
    -0.54
    %。
    -0.52
     Com
    -0.52
     iſt
    -0.52
    POSITIVE LOGITS
    AndEndTag
    0.76
    ValueStyle
    0.76
    XmlAccessType
    0.68
     ddelweddau
    0.51
     Normdatei
    0.47
    ьаж
    0.45
    под
    0.45
     acute
    0.45
    GAB
    0.45
    XmlEnum
    0.45
    Activations Density 0.082%

    No Known Activations