© 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. 77696
    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
    xane
    -0.48
    shub
    -0.47
    sof
    -0.45
     chấm
    -0.44
    kespea
    -0.43
    estacks
    -0.43
    न्दु
    -0.43
     Swar
    -0.43
    MAK
    -0.42
    stuhl
    -0.41
    POSITIVE LOGITS
    Portail
    0.72
     تضيفلها
    0.71
    帖最后由
    0.68
    IVEREF
    0.65
     termica
    0.64
    (!__
    0.64
     juridiques
    0.59
     NSCoder
    0.59
     koper
    0.58
    RefNanny
    0.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.