© 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. 72343
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act-logits · 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
    XVI
    -0.70
     surla
    -0.68
     ujednoznacz
    -0.68
     Signalez
    -0.65
    ThroughAttribute
    -0.64
     Sixteen
    -0.62
    AnimationsModule
    -0.61
     fifteenth
    -0.61
     StatefulWidget
    -0.60
     XVI
    -0.59
    POSITIVE LOGITS
    2
    0.56
     chiff
    0.46
     series
    0.44
    heben
    0.42
     dop
    0.41
     Pard
    0.40
    Ģ
    0.40
     Series
    0.40
     dw
    0.40
    mpia
    0.40
    Activations Density 0.004%

    No Known Activations