© 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. 78289
    Prev
    Next
    INDEX
    Explanations

    Unrelated text snippets

    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
    posedge
    -1.13
     HttpNotFound
    -0.94
    StandardCharsets
    -0.91
    writeFieldEnd
    -0.88
     '\\;'
    -0.88
    complexContent
    -0.85
     виправивши
    -0.84
    ConstraintMaker
    -0.84
    writeField
    -0.84
    onAttach
    -0.83
    POSITIVE LOGITS
     key
    0.62
     back
    0.49
    key
    0.44
     Key
    0.39
    Key
    0.39
     Back
    0.39
     remote
    0.36
     tro
    0.34
    KEY
    0.34
    back
    0.34
    Activations Density 0.000%

    No Known Activations