© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42630
    Prev
    Next
    INDEX
    Explanations

    reporting

    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
    SuppressMessage
    -0.60
    DECREF
    -0.54
    aspectj
    -0.54
     مشين
    -0.52
     WaitForSeconds
    -0.52
    IBILITIES
    -0.52
    NOPQRST
    -0.51
     for
    -0.49
    around
    -0.49
    adaş
    -0.48
    POSITIVE LOGITS
     pleaſure
    0.68
     cauſe
    0.68
     reaſon
    0.67
     diſt
    0.65
     purpoſe
    0.64
     ſen
    0.63
     Spisak
    0.63
     uſe
    0.63
     houſe
    0.63
     juſt
    0.62
    Activations Density 0.147%

    No Known Activations