© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93990
    Prev
    Next
    INDEX
    Explanations

    The

    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
     Roskov
    -0.90
    期刊论文
    -0.90
     дописавши
    -0.88
     متعلقه
    -0.88
    المناصب
    -0.81
     colorés
    -0.81
    MENAFN
    -0.79
    tagHelperRunner
    -0.79
     larmes
    -0.78
    +#+#
    -0.78
    POSITIVE LOGITS
    いわゆる
    0.33
     histor
    0.31
    เอง
    0.28
     so
    0.27
     history
    0.26
    stateProvider
    0.26
     generalized
    0.26
    >*/
    0.26
    วัติ
    0.25
     histori
    0.25
    Activations Density 0.001%

    No Known Activations