© 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. 2493
    Prev
    Next
    INDEX
    Explanations

    as

    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
    who
    -0.45
    him
    -0.44
    friend
    -0.43
     parar
    -0.42
    ARDO
    -0.42
     ότι
    -0.42
    Device
    -0.41
     how
    -0.41
    too
    -0.41
    flush
    -0.41
    POSITIVE LOGITS
    SourceChecksum
    0.94
    RenderAtEndOf
    0.84
    ंदीखरीदारी
    0.82
    MemoryWarning
    0.81
    TypedDataSet
    0.79
    StoryboardSegue
    0.79
     autorytatywna
    0.72
    ########.
    0.71
     AssemblyProduct
    0.71
    ConstraintMaker
    0.71
    Activations Density 0.000%

    No Known Activations