© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3043
    Prev
    Next
    INDEX
    Explanations

    binary

    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
    ]._
    -0.61
    ."</
    -0.59
    '],
    -0.57
     itſelf
    -0.56
    .";
    -0.56
    .。
    -0.55
    '},
    -0.54
    ]";
    -0.54
    <bos>
    -0.53
    Diwedd
    -0.53
    POSITIVE LOGITS
    ↵
    0.82
    +#+#
    0.68
     فريبيس
    0.65
     TextInputType
    0.54
    ArgsConstructor
    0.53
     MaterialApp
    0.52
     跳转至
    0.50
     &
    0.47
    OGND
    0.47
    cshtml
    0.47
    Activations Density 0.010%

    No Known Activations