© 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. 91992
    Prev
    Next
    INDEX
    Explanations

    that

    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
    RegistryLite
    -0.75
     diesen
    -0.63
    väg
    -0.56
    tagext
    -0.56
     diese
    -0.56
    \'{
    -0.55
     igång
    -0.55
    this
    -0.55
     ifrån
    -0.55
     aquest
    -0.53
    POSITIVE LOGITS
     though
    0.71
     although
    0.70
     despite
    0.60
    basicConfig
    0.60
    <bos>
    0.60
    ↵↵
    0.59
     even
    0.58
     according
    0.57
     while
    0.57
     since
    0.54
    Activations Density 0.002%

    No Known Activations