© 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. 0-CLT-HP
    7. 41130
    Prev
    Next
    INDEX
    Explanations

    shadow

    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
     shadow
    -0.79
     myſelf
    -0.77
     enfans
    -0.76
     avoient
    -0.74
     étoient
    -0.73
     ainfi
    -0.71
     argint
    -0.69
     brancas
    -0.69
     auroit
    -0.69
    Shadow
    -0.66
    POSITIVE LOGITS
    ISATION
    0.65
    ness
    0.60
      (
    0.54
    sivity
    0.53
     autorytatywna
    0.53
    ESTY
    0.53
    COMES
    0.52
    absent
    0.52
    {}",
    0.52
    ship
    0.50
    Activations Density 0.093%

    No Known Activations