© 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. 5-CLT-HP
    7. 97906
    Prev
    Next
    INDEX
    Explanations

    entry

    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
     Meksiku
    -0.65
    formik
    -0.64
    ()?;
    -0.60
    
    -0.56
    ніципа
    -0.51
    flickr
    -0.49
    Вла
    -0.45
    ClientSize
    -0.44
    цездатний
    -0.43
     pubb
    -0.43
    POSITIVE LOGITS
     for
    0.85
    ⓘ
    0.61
     Audiodateien
    0.60
     about
    0.57
    regarding
    0.56
     regarding
    0.55
     summarizing
    0.55
     denoting
    0.54
    สำหรับ
    0.54
     relating
    0.54
    Activations Density 0.001%

    No Known Activations