© 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. 76762
    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
    nader
    -0.48
     Ach
    -0.47
     Essen
    -0.46
    runt
    -0.44
    IntoConstraints
    -0.43
     Cologne
    -0.43
    anta
    -0.42
    ચ
    -0.42
    ben
    -0.42
     ach
    -0.42
    POSITIVE LOGITS
    WithIOException
    0.73
    ItemBackground
    0.69
    Przypisy
    0.66
    Autoritní
    0.64
     gynhyrchwyd
    0.61
    fromnode
    0.60
     autorytatywna
    0.60
    hdys
    0.58
    uxxxx
    0.57
    luia
    0.56
    Activations Density 0.001%

    No Known Activations