© 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. 91152
    Prev
    Next
    INDEX
    Explanations

    Supplemental

    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
     Monfieur
    -0.83
     myſelf
    -0.73
     faſt
    -0.70
     Theſe
    -0.70
     poffible
    -0.68
     purpoſe
    -0.67
    [::-
    -0.66
     themſelves
    -0.66
     chofe
    -0.66
    BeginContext
    -0.63
    POSITIVE LOGITS
     فريبيس
    0.56
     lenker
    0.54
    InitVars
    0.49
     n
    0.47
    Външни
    0.44
     recens
    0.42
     gran
    0.41
     ligiloj
    0.41
    wiada
    0.40
    vestido
    0.40
    Activations Density 0.000%

    No Known Activations