© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2607
    Prev
    Next
    INDEX
    Explanations

    Adjectives

    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
     choices
    -0.63
     news
    -0.61
     investments
    -0.57
     preparations
    -0.56
     discussion
    -0.54
     history
    -0.54
     efforts
    -0.54
     choice
    -0.54
     progress
    -0.53
     advice
    -0.53
    POSITIVE LOGITS
     juger
    0.72
    Personensuche
    0.71
     traités
    0.70
     refusé
    0.68
     chrétiens
    0.68
     dévelo
    0.67
     lèvres
    0.66
     cérami
    0.66
     miei
    0.66
     présentés
    0.65
    Activations Density 0.008%

    No Known Activations