© 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. 96973
    Prev
    Next
    INDEX
    Explanations

    stress, ways of doing

    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
     Normdatei
    -0.50
     indisponible
    -0.47
    OURI
    -0.44
     AssemblyCompany
    -0.44
     Berech
    -0.43
    which
    -0.43
     cref
    -0.43
    Œuvres
    -0.43
     purpure
    -0.42
    cokinetic
    -0.42
    POSITIVE LOGITS
     Paglinawan
    0.72
    HEET
    0.69
    tagHelperRunner
    0.68
    المناصب
    0.67
    kuuta
    0.64
     صوتيه
    0.62
     withdrawing
    0.60
     فريبيس
    0.58
    Jereo
    0.57
    runOnUiThread
    0.56
    Activations Density 0.001%

    No Known Activations