© 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. 94114
    Prev
    Next
    INDEX
    Explanations

    Inter/Super

    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
     so
    -0.49
    posedge
    -0.48
     come
    -0.47
     for
    -0.47
     
    -0.44
     the
    -0.41
     up
    -0.41
     her
    -0.41
     der
    -0.40
     like
    -0.40
    POSITIVE LOGITS
     fumée
    0.91
     aikaa
    0.81
     stället
    0.81
    voltaic
    0.79
     florales
    0.77
     larmes
    0.76
     normaux
    0.76
     cérami
    0.75
     étoient
    0.75
     colorés
    0.74
    Activations Density 0.378%

    No Known Activations