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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41188
    Prev
    Next
    INDEX
    Explanations

    spacer

    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
     c
    -0.57
     ban
    -0.55
    jona
    -0.55
     reg
    -0.54
     pad
    -0.54
    XmlAccessorType
    -0.50
     d
    -0.49
     dens
    -0.48
    grana
    -0.47
     mess
    -0.47
    POSITIVE LOGITS
     bogotá
    0.77
     doubtnut
    0.69
     kysy
    0.67
     Anſ
    0.66
     ainfi
    0.66
     démocr
    0.65
     Италијани
    0.65
     RIPRODUZIONE
    0.64
     Monfieur
    0.64
     purpoſe
    0.63
    Activations Density 1.632%

    No Known Activations