© 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. 4-CLT-HP
    7. 372
    Prev
    Next
    INDEX
    Explanations

    conjunctions/punctuation

    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
    Datuak
    -0.65
     الحره
    -0.65
    GOTREF
    -0.65
     onCreateView
    -0.61
     تانيه
    -0.58
    Glej
    -0.57
     يتيمه
    -0.57
    WriteBarrier
    -0.57
    ̓
    -0.56
     kanyang
    -0.55
    POSITIVE LOGITS
     of
    1.20
     their
    0.74
     Their
    0.71
    Their
    0.71
     leurs
    0.66
     They
    0.66
    their
    0.63
    彼らは
    0.62
     they
    0.61
     mereka
    0.61
    Activations Density 0.008%

    No Known Activations