© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77643
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    SBATCH
    -0.66
    principalColumn
    -0.65
    rungsseite
    -0.65
     utafitiHapana
    -0.63
     AssemblyTitle
    -0.63
    XmlEnum
    -0.62
    antMatchers
    -0.60
     "..\..\..\
    -0.60
    sizeCache
    -0.60
    رشف
    -0.59
    POSITIVE LOGITS
     over
    0.52
     door
    0.48
    uaire
    0.47
    chandra
    0.44
     throughout
    0.44
     blocks
    0.42
     Privacidade
    0.40
     houses
    0.40
     maisha
    0.40
     Sus
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.