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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1472
    Prev
    Next
    INDEX
    Explanations

    Provides information/context

    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
    MemoryWarning
    -0.77
     autorytatywna
    -0.72
     "..\..\..\
    -0.72
    IntoConstraints
    -0.72
    SequentialGroup
    -0.71
     Roskov
    -0.71
    UnusedPrivate
    -0.69
    )}</
    -0.66
    coming
    -0.65
     AssemblyVersion
    -0.64
    POSITIVE LOGITS
     terms
    0.96
     my
    0.71
     (
    0.68
     the
    0.63
     term
    0.62
     términos
    0.60
    Terms
    0.57
     there
    0.57
     Term
    0.56
     Terms
    0.56
    Activations Density 0.006%

    No Known Activations