© 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. 4625
    Prev
    Next
    INDEX
    Explanations

    Comma

    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
     تضيفلها
    -0.61
    Personendaten
    -0.56
     noten
    -0.52
    aarrggbb
    -0.51
    webElementGuid
    -0.50
    StreetMap
    -0.50
    CompilerServices
    -0.50
     Италијани
    -0.50
    speakers
    -0.49
    netbeans
    -0.49
    POSITIVE LOGITS
    ↵↵
    0.69
     conforman
    0.60
    tvguidetime
    0.59
    sizeCache
    0.57
    You
    0.55
     That
    0.53
    <eos>
    0.53
    These
    0.52
    السكان
    0.52
    ↵
    0.52
    Activations Density 0.033%

    No Known Activations