© 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. 96581
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    UnsafeEnabled
    -1.06
    RenderAtEndOf
    -1.03
    sizeCache
    -1.00
    tonode
    -1.00
     kasarigan
    -0.95
    Tikang
    -0.93
    ImageContext
    -0.90
    InputBorder
    -0.90
    ScopeManager
    -0.87
    WriteBarrier
    -0.81
    POSITIVE LOGITS
     bero
    0.43
    0
    0.41
    2
    0.40
    7
    0.39
    5
    0.36
    4
    0.36
     
    0.35
    1
    0.34
    6
    0.33
    setcounter
    0.33
    Activations Density 0.002%

    No Known Activations