© 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. 1-CLT-HP
    7. 16199
    Prev
    Next
    INDEX
    Explanations

    mobil

    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
     mobili
    -0.75
     mobil
    -0.72
    mobili
    -0.68
     mobilization
    -0.68
    Mob
    -0.65
     Mob
    -0.64
    mobil
    -0.63
    Mobil
    -0.63
     mobilized
    -0.61
     mobilisation
    -0.61
    POSITIVE LOGITS
    ToBounds
    0.63
    )</
    0.53
    Naissance
    0.51
    ulz
    0.51
    Activités
    0.51
    }';
    0.51
    Harmony
    0.49
     Thermostat
    0.49
    documentclass
    0.48
     Aristote
    0.48
    Activations Density 0.034%

    No Known Activations