© 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. 77768
    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
     propOrder
    -0.86
    Tikang
    -0.83
     Roskov
    -0.82
    abestanden
    -0.79
     виправивши
    -0.75
    MemoryWarning
    -0.74
    Personendaten
    -0.72
    ScopeManager
    -0.71
    DrawerToggle
    -0.71
    脚注の使い方
    -0.69
    POSITIVE LOGITS
     off
    0.68
     over
    0.57
     center
    0.51
    off
    0.51
     hold
    0.47
     stage
    0.46
     voting
    0.45
     charge
    0.44
    éta
    0.43
     wheel
    0.43
    Activations Density 0.000%

    No Known Activations