© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43486
    Prev
    Next
    INDEX
    Explanations

    free

    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
     free
    -1.77
     Free
    -1.35
    free
    -1.23
    Free
    -1.21
     FREE
    -1.13
    FREE
    -0.98
     свобод
    -0.90
     беспла
    -0.87
     bebas
    -0.84
    免费
    -0.82
    POSITIVE LOGITS
     resourceCulture
    1.16
    脚注の使い方
    1.16
    TypedDataSet
    1.14
    ValueStyle
    1.12
    awtextra
    1.09
     дописавши
    1.08
    Hochspringen
    1.07
    ReusableCell
    1.07
     TestBed
    1.04
    IUrlHelper
    1.04
    Activations Density 0.217%

    No Known Activations