© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75322
    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
    4
    -0.53
     fourth
    -0.50
     four
    -0.40
    ेष
    -0.40
     constant
    -0.39
    me
    -0.37
    ృ
    -0.37
     FOURTH
    -0.36
     Fourth
    -0.35
    septic
    -0.34
    POSITIVE LOGITS
     Roskov
    0.83
     kasarigan
    0.77
    SequentialGroup
    0.76
    SourceChecksum
    0.76
     autorytatywna
    0.75
    rungsseite
    0.73
    ագրություններ
    0.71
     /\.(
    0.71
     OFDb
    0.68
    XmlAccessType
    0.66
    Activations Density 0.002%

    No Known Activations