© 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. 1-CLT-HP
    7. 10413
    Prev
    Next
    INDEX
    Explanations

    these/those

    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
     have
    -0.75
     happen
    -0.70
     are
    -0.69
    have
    -0.68
     HAVE
    -0.66
    CompilerServices
    -0.66
     remain
    -0.64
     aren
    -0.60
     go
    -0.58
     seem
    -0.58
    POSITIVE LOGITS
     runs
    0.75
     moves
    0.74
     applies
    0.72
     installs
    0.71
     binds
    0.71
     nahilalakip
    0.70
     develops
    0.69
     acts
    0.69
     begins
    0.69
     adds
    0.68
    Activations Density 0.020%

    No Known Activations