© 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. 605
    Prev
    Next
    INDEX
    Explanations

    practice

    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
     about
    -0.64
    ese
    -0.48
    wikk
    -0.47
    ValueStyle
    -0.47
    ESE
    -0.44
    ↵↵
    -0.44
     Ender
    -0.43
     people
    -0.42
     Sou
    -0.41
     the
    -0.40
    POSITIVE LOGITS
    StoreMessageInfo
    0.79
     poffible
    0.76
     neceffary
    0.74
     itſelf
    0.71
     Undeclared
    0.69
     reaſon
    0.69
     myſelf
    0.68
     viſ
    0.68
     purpoſe
    0.66
     kaarangay
    0.66
    Activations Density 0.471%

    No Known Activations