© 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. 12065
    Prev
    Next
    INDEX
    Explanations

    Vitamin B

    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
    }],
    -0.56
    loyment
    -0.54
     Gaulle
    -0.54
    ミナル
    -0.52
     sää
    -0.52
     Sider
    -0.52
     kvä
    -0.50
    antur
    -0.49
     Satis
    -0.49
     Cod
    -0.47
    POSITIVE LOGITS
    principalColumn
    0.71
     disambiguazione
    0.63
    providedIn
    0.60
    wpi
    0.57
    StructEnd
    0.51
     propOrder
    0.50
    mergeFrom
    0.47
    httphttps
    0.47
     Zwie
    0.47
     caucus
    0.47
    Activations Density 0.144%

    No Known Activations