© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93263
    Prev
    Next
    INDEX
    Explanations

    not

    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
     misura
    -0.54
    <bos>
    -0.54
     gezien
    -0.51
     venons
    -0.50
     băr
    -0.49
     живота
    -0.49
     américains
    -0.48
    зайн
    -0.48
     vidas
    -0.47
     chré
    -0.47
    POSITIVE LOGITS
     great
    0.71
     للاسماء
    0.70
     ModelExpression
    0.70
     CreateTagHelper
    0.69
    ?")
    0.67
    ?')
    0.66
    Дереккөздер
    0.66
     ISNI
    0.66
    ]));
    0.62
    \{\\
    0.60
    Activations Density 0.005%

    No Known Activations