© 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. 5-CLT-HP
    7. 91699
    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
    Satis
    -0.52
     voorbij
    -0.47
     anello
    -0.46
    thur
    -0.46
     laiton
    -0.43
     justa
    -0.43
    förmig
    -0.43
     juos
    -0.43
     splet
    -0.43
     SwitchCompat
    -0.42
    POSITIVE LOGITS
     дописавши
    0.96
     <",
    0.82
    resave
    0.82
     &___
    0.74
     transférez
    0.74
    httphttps
    0.73
     Numerade
    0.73
    __':
    0.71
    TagMode
    0.70
    StoryboardSegue
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.