© 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. 5-CLT-HP
    7. 91229
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    EndTag
    -0.71
    Jeografia
    -0.70
    ENEFITS
    -0.64
     يتيمه
    -0.63
    ̍t
    -0.62
    DebuggerStep
    -0.61
    IonicModule
    -0.61
    WithIOException
    -0.61
    انجليز
    -0.60
    ipun
    -0.59
    POSITIVE LOGITS
     ModelExpression
    0.49
    complexType
    0.44
     connexes
    0.43
     miel
    0.41
    Hochspringen
    0.40
     assurent
    0.40
     Diakses
    0.39
      
    0.39
     &___
    0.39
     poursu
    0.38
    Activations Density 0.019%

    No Known Activations