© 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. 0-CLT-HP
    7. 93874
    Prev
    Next
    INDEX
    Explanations

    Suffixes

    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
     
    -0.74
    _
    -0.69
    ↵↵
    -0.62
    ↵
    -0.62
     of
    -0.62
    .
    -0.60
    1
    -0.58
        
    -0.58
     the
    -0.57
    S
    -0.57
    POSITIVE LOGITS
    tvguidetime
    1.34
    ConstraintMaker
    1.26
    setVerticalGroup
    1.20
     NSCoder
    1.20
     démocr
    1.19
     AssemblyProduct
    1.18
    GEBURTSDATUM
    1.18
    PreferredItem
    1.16
     AssemblyCulture
    1.14
    SequentialGroup
    1.10
    Activations Density 0.068%

    No Known Activations