© 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. 42615
    Prev
    Next
    INDEX
    Explanations

    presence of numerical data

    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
     purpoſe
    -2.17
     myſelf
    -2.14
     itſelf
    -2.09
     Monfieur
    -2.09
     Majefty
    -2.08
     pleaſure
    -2.08
     Jefus
    -2.02
     ſtate
    -2.02
     Reſ
    -2.00
     Efq
    -2.00
    POSITIVE LOGITS
     "
    1.11
    )
    1.07
     “
    1.05
     I
    0.99
     ‘
    0.99
     '
    0.98
    ),
    0.95
    .
    0.94
    ,
    0.94
    <eos>
    0.93
    Activations Density 0.299%

    No Known Activations