© 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. 4589
    Prev
    Next
    INDEX
    Explanations

    the

    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
     propOrder
    -0.70
    AutoScale
    -0.69
    WebElementEntity
    -0.63
    ")));
    -0.61
    HasKey
    -0.59
    <()>
    -0.59
    abestanden
    -0.58
    ⓧ
    -0.56
     defaultstate
    -0.56
    "])){
    -0.55
    POSITIVE LOGITS
    Viitteet
    0.57
     walls
    0.54
     wall
    0.52
     بيها
    0.52
     spic
    0.51
    xase
    0.51
     FBref
    0.50
    blick
    0.50
     []:
    0.49
    StoryboardSegue
    0.47
    Activations Density 0.003%

    No Known Activations