© 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. 5-CLT-HP
    7. 3295
    Prev
    Next
    INDEX
    Explanations

    commitment

    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
    IntoConstraints
    -0.68
    LookAnd
    -0.59
    XtraGrid
    -0.57
     ſtate
    -0.57
    ScopeManager
    -0.56
    Према
    -0.56
     ſon
    -0.55
    horabuena
    -0.55
    enumi
    -0.54
     nivå
    -0.54
    POSITIVE LOGITS
     ourselves
    0.64
     serving
    0.60
     serve
    0.60
     service
    0.57
     living
    0.54
     work
    0.54
    serve
    0.52
     working
    0.50
     use
    0.50
     non
    0.50
    Activations Density 0.004%

    No Known Activations