© 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. 94886
    Prev
    Next
    INDEX
    Explanations

    a

    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
     was
    -1.13
     had
    -0.90
     Was
    -0.88
     were
    -0.87
     wasn
    -0.84
    Was
    -0.82
     did
    -0.75
     gave
    -0.75
    was
    -0.74
     weren
    -0.71
    POSITIVE LOGITS
     Monfieur
    0.78
     nakalista
    0.75
     ་་
    0.75
     ſever
    0.74
     purpoſe
    0.74
     theſe
    0.74
     Spisak
    0.74
     pleaſure
    0.73
     myſelf
    0.73
     iſt
    0.72
    Activations Density 0.069%

    No Known Activations