© 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. 0-CLT-HP
    7. 41386
    Prev
    Next
    INDEX
    Explanations

    filed

    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
     noires
    -0.83
     financières
    -0.82
     doccia
    -0.74
     pourrez
    -0.70
     lèvres
    -0.68
     tiroirs
    -0.68
     fondament
    -0.67
     réguli
    -0.67
     jouets
    -0.67
     nationaux
    -0.67
    POSITIVE LOGITS
     a
    0.77
     the
    0.75
     improvements
    0.65
     an
    0.63
     
    0.61
    jws
    0.58
     everything
    0.57
     Havel
    0.56
     its
    0.56
    remacy
    0.56
    Activations Density 0.122%

    No Known Activations