© 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. 20-CLT-HP
    7. 71614
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    np_max-act-logits · 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
    TargetException
    -0.53
    httphttps
    -0.49
    RegistryLite
    -0.48
    __':
    -0.46
    υνα
    -0.46
     Pati
    -0.43
     flit
    -0.43
    styleable
    -0.43
    やま
    -0.42
     agré
    -0.42
    POSITIVE LOGITS
     noires
    0.64
    нциклопедия
    0.63
     oreilles
    0.61
     varandra
    0.58
     avoient
    0.57
     polvere
    0.57
     étoient
    0.56
     propOrder
    0.56
     rayures
    0.56
    bise
    0.55
    Activations Density 0.009%

    No Known Activations