© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10926
    Prev
    Next
    INDEX
    Explanations

    are

    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
    are
    -0.71
    ARE
    -0.61
     governed
    -0.55
     nød
    -0.55
    EDEFAULT
    -0.53
    OGND
    -0.52
     Wiktionnaire
    -0.51
     reliant
    -0.50
     vying
    -0.50
     فريبيس
    -0.50
    POSITIVE LOGITS
    y
    0.65
     يتيمه
    0.60
     veckor
    0.59
    kháu
    0.54
     باخ
    0.53
    nappropriate
    0.53
     ceci
    0.52
    gno
    0.51
     assure
    0.51
    fully
    0.50
    Activations Density 0.028%

    No Known Activations