© 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. 41262
    Prev
    Next
    INDEX
    Explanations

    AKS

    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
     Efq
    -1.51
     myſelf
    -1.39
     photolibrary
    -1.38
     itſelf
    -1.38
    ſelves
    -1.38
     ―――――
    -1.38
     ་་
    -1.37
    ſelf
    -1.30
     Мексичка
    -1.30
     ſind
    -1.29
    POSITIVE LOGITS
    s
    1.59
    a
    1.11
    ی
    0.99
    ing
    0.91
    i
    0.90
    y
    0.86
    o
    0.82
    t
    0.71
    ed
    0.71
    e
    0.71
    Activations Density 0.081%

    No Known Activations