© 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. 95101
    Prev
    Next
    INDEX
    Explanations

    actions or processes

    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
     Theſe
    -1.56
     myſelf
    -1.52
     Monfieur
    -1.51
     ſeveral
    -1.37
     fubject
    -1.36
     feroit
    -1.35
     uſed
    -1.34
     étoit
    -1.32
     avoient
    -1.32
     étoient
    -1.31
    POSITIVE LOGITS
     A
    0.98
     F
    0.89
     
    0.87
     H
    0.85
     New
    0.84
     And
    0.84
     L
    0.82
     So
    0.82
    <eos>
    0.81
     Car
    0.81
    Activations Density 0.149%

    No Known Activations