© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 4110
    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
     faciles
    -0.54
    PerformLayout
    -0.46
     and
    -0.45
    Portale
    -0.45
    ArgsConstructor
    -0.44
     giapp
    -0.44
     genoux
    -0.44
     svol
    -0.43
     bocetos
    -0.42
     engraçadas
    -0.41
    POSITIVE LOGITS
    ...)
    0.79
    ...')
    0.77
     %)
    0.73
    ?')
    0.71
    CppMethod
    0.71
    ...")
    0.71
    )?
    0.71
    *)
    0.71
     \%)
    0.70
    ?")
    0.69
    Activations Density 0.004%

    No Known Activations