© 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. 4833
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    InputBorder
    -0.95
    <bos>
    -0.89
    +#+#
    -0.88
     AssemblyCulture
    -0.79
     ITIS
    -0.78
     للاسماء
    -0.77
     kasarigan
    -0.77
     Вікі
    -0.76
    ]")]
    -0.75
    jspx
    -0.74
    POSITIVE LOGITS
     also
    0.45
    ulico
    0.40
     bước
    0.36
    区
    0.36
     incorporate
    0.35
    去的
    0.35
    us
    0.35
     incorpor
    0.35
     synd
    0.35
    ("."
    0.35
    Activations Density 0.003%

    No Known Activations