© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95665
    Prev
    Next
    INDEX
    Explanations

    permitted

    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
    Negative Logits
     Se
    -0.67
    enumii
    -0.59
    Se
    -0.56
     permitted
    -0.56
     prohibited
    -0.56
     eliminate
    -0.55
     while
    -0.54
    clusion
    -0.51
    gor
    -0.51
     excused
    -0.51
    POSITIVE LOGITS
     Efq
    0.64
     متعلقه
    0.64
    EndProject
    0.64
     Anſ
    0.63
     becauſe
    0.61
    SequentialGroup
    0.60
    ſelf
    0.59
    Хьажоргаш
    0.56
    ycznych
    0.54
    Derbyniad
    0.54
    Activations Density 0.043%

    No Known Activations