© 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. 5-CLT-HP
    7. 5194
    Prev
    Next
    INDEX
    Explanations

    "Let's" start of sentences

    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
     auroit
    -0.66
    SharedDtor
    -0.60
     klokken
    -0.60
     avoient
    -0.59
     feroit
    -0.57
     pouvoit
    -0.57
    IInterface
    -0.57
     yoktur
    -0.55
     étoit
    -0.52
    CodedInputStream
    -0.51
    POSITIVE LOGITS
     Now
    0.85
     now
    0.84
     some
    0.70
     those
    0.63
     a
    0.59
    !...
    0.58
     another
    0.56
     StatelessWidget
    0.56
     then
    0.56
    …”
    0.56
    Activations Density 0.006%

    No Known Activations