© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92557
    Prev
    Next
    INDEX
    Explanations

    -ing

    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
    ,
    -0.42
    Ditto
    -0.41
     when
    -0.40
    :
    -0.39
    —
    -0.39
    .
    -0.38
     Incidentally
    -0.38
    Nyc
    -0.38
     cuando
    -0.38
    --
    -0.38
    POSITIVE LOGITS
    ViewImports
    0.89
     فريبيس
    0.82
    MemoryWarning
    0.75
    IsMutable
    0.74
     avoit
    0.72
    IsContent
    0.72
    SBATCH
    0.69
    Архівовано
    0.69
     pinulongan
    0.69
     myſelf
    0.68
    Activations Density 0.003%

    No Known Activations