© 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. 1-CLT-HP
    7. 11980
    Prev
    Next
    INDEX
    Explanations

    group

    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
     group
    -0.62
     groep
    -0.54
    +#+
    -0.51
    Группа
    -0.51
     posse
    -0.48
     gruppo
    -0.47
     crew
    -0.47
    DIPSETTING
    -0.46
     grupo
    -0.44
    group
    -0.43
    POSITIVE LOGITS
     noires
    0.61
    AttributeValue
    0.58
     présidenti
    0.56
    rzost
    0.55
    ahul
    0.55
    EndInit
    0.55
    дарь
    0.54
    aville
    0.54
    catraz
    0.54
     parall
    0.53
    Activations Density 0.007%

    No Known Activations