© 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. 4-CLT-HP
    7. 2002
    Prev
    Next
    INDEX
    Explanations

    graphs and plots

    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
    __':
    -0.70
     vänner
    -0.66
     meubles
    -0.64
    RenderAtEndOf
    -0.64
     télécharge
    -0.61
     poffible
    -0.60
     enfans
    -0.60
    inSlope
    -0.59
     étoient
    -0.57
     étoit
    -0.57
    POSITIVE LOGITS
    <bos>
    0.57
     initComponents
    0.55
     give
    0.52
     incorporate
    0.50
     connect
    0.50
     sche
    0.48
    tdessen
    0.48
     enclose
    0.47
     terminate
    0.46
     stand
    0.46
    Activations Density 0.005%

    No Known Activations