© 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. 5-CLT-HP
    4. 2242
    Prev
    Next
    INDEX
    Explanations

    t

    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
    SizeF
    -0.72
    ########.
    -0.65
    tagHelperRunner
    -0.65
    only
    -0.62
    تفصیلات
    -0.60
     onely
    -0.60
     eenvou
    -0.59
    存于互联网档案馆
    -0.57
     Neglect
    -0.57
    NullException
    -0.56
    POSITIVE LOGITS
     always
    0.63
     technically
    0.59
     specifically
    0.56
     yet
    0.54
    日閲覧
    0.52
     eventually
    0.51
     ultimately
    0.51
    ALWAYS
    0.51
     usually
    0.49
     téc
    0.48
    Activations Density 0.001%

    No Known Activations