© 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. 5-CLT-HP
    7. 97551
    Prev
    Next
    INDEX
    Explanations

    leader titles

    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
    🧵
    -0.47
    ETERS
    -0.45
    []>(
    -0.44
    antes
    -0.44
    al
    -0.44
    ifikant
    -0.44
    ी
    -0.44
    webElementGuid
    -0.43
    a
    -0.43
    ه
    -0.43
    POSITIVE LOGITS
    ngdoc
    0.79
    存于互联网档案馆
    0.71
    mogat
    0.65
     دیکھیے
    0.61
    encanaan
    0.61
     crescere
    0.61
     Majefty
    0.59
    Pautan
    0.59
    ésor
    0.59
     ainfi
    0.58
    Activations Density 0.003%

    No Known Activations