© 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. 5136
    Prev
    Next
    INDEX
    Explanations

    code and debugging

    np_max-act · gemini-2.0-flash
    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
     Jinping
    -0.65
    anganronpa
    -0.47
    ndx
    -0.44
     Hyd
    -0.43
    ponible
    -0.43
     fince
    -0.41
    Glad
    -0.41
    readline
    -0.41
    icznie
    -0.40
    sburg
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.80
    CloseOperation
    0.75
     MainAxisSize
    0.75
    TagMode
    0.70
     MOB
    0.66
    MOB
    0.60
    posedge
    0.60
     بيها
    0.60
    MO
    0.59
    ագրություններ
    0.59
    Activations Density 0.001%

    No Known Activations