© 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. 5-CLT-HP
    7. 6092
    Prev
    Next
    INDEX
    Explanations

    since

    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
     These
    -0.58
     Someone
    -0.52
    These
    -0.51
    someone
    -0.50
    Someone
    -0.48
    这些人
    -0.47
    umbres
    -0.46
     everyone
    -0.46
     fiecare
    -0.46
    互联网档案馆
    -0.45
    POSITIVE LOGITS
     its
    0.78
     ujednoznacz
    0.69
    BufferException
    0.68
     resourceCulture
    0.61
    AutoresizingMask
    0.59
     my
    0.59
    __':
    0.58
     miei
    0.53
    nologue
    0.53
     inception
    0.52
    Activations Density 0.004%

    No Known Activations