© 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. 91664
    Prev
    Next
    INDEX
    Explanations

    tumors

    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
    מבר
    -0.54
     الرياضيه
    -0.52
     发表于
    -0.47
    円
    -0.47
    іга
    -0.47
     judíos
    -0.46
     وتسجيلات
    -0.45
    guém
    -0.45
    xtext
    -0.45
    makeConstraints
    -0.44
    POSITIVE LOGITS
     iſt
    0.69
     Signalez
    0.65
     itſelf
    0.63
    WriteTagHelper
    0.59
     vulgaires
    0.59
    });*/
    0.58
    })*/
    0.58
     мәкалә
    0.57
    ſelves
    0.57
     bezeichneter
    0.56
    Activations Density 0.297%

    No Known Activations