© 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. 0-CLT-HP
    7. 43194
    Prev
    Next
    INDEX
    Explanations

    theft

    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
     taught
    -1.05
    i
    -0.77
    taught
    -0.72
     متعلقه
    -0.71
    listed
    -0.65
     noticed
    -0.64
     Taught
    -0.62
     limited
    -0.61
    fund
    -0.61
    cess
    -0.60
    POSITIVE LOGITS
    QMetaType
    0.56
    RenderAtEndOf
    0.53
     Pen
    0.51
     Pob
    0.51
     ProtoMessage
    0.50
     Lam
    0.50
    AutoScale
    0.50
     Ap
    0.50
    AndEndTag
    0.49
    vaadin
    0.49
    Activations Density 0.146%

    No Known Activations