© 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. 2462
    Prev
    Next
    INDEX
    Explanations

    Problems and issues

    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
    IUrlHelper
    -0.76
    gives
    -0.58
    pires
    -0.56
    AnimationsModule
    -0.54
     gives
    -0.53
    yttää
    -0.51
    ENODEV
    -0.50
     happens
    -0.48
     occurs
    -0.48
     goes
    -0.48
    POSITIVE LOGITS
     estekak
    0.67
    .;
    0.62
    .
    0.60
    usercontent
    0.59
    Handlung
    0.57
    তথ্যসূত্র
    0.57
     resourceCulture
    0.56
    AndEndTag
    0.55
    ；
    0.54
    awtextra
    0.53
    Activations Density 0.002%

    No Known Activations