© 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. 98238
    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
     rock
    -0.74
     stone
    -0.70
     Rock
    -0.67
     Stone
    -0.62
    rock
    -0.60
    Rock
    -0.59
     rocks
    -0.54
     ROCK
    -0.54
     stones
    -0.49
     STONE
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.87
     InputDecoration
    0.86
    новништво
    0.79
    évaluateur
    0.79
     محفوظة
    0.77
     propOrder
    0.77
    tanleria
    0.72
    noons
    0.71
    GOTREF
    0.71
    URLException
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.