© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 72547
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · 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
     in
    -0.57
    WITH
    -0.54
    expandindo
    -0.53
    OF
    -0.51
     dalam
    -0.49
     в
    -0.47
    postmedia
    -0.47
    而在
    -0.46
     nelle
    -0.45
     în
    -0.45
    POSITIVE LOGITS
     from
    1.80
    from
    1.21
     From
    1.15
     từ
    1.14
     FROM
    1.09
    From
    1.06
     från
    1.06
     desde
    0.98
    จาก
    0.97
     therefrom
    0.95
    Activations Density 0.019%

    No Known Activations