Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39565
    Prev
    Next
    INDEX
    Explanations

    acronyms

    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
    MLLoader
    -1.03
    EDEFAULT
    -0.96
    ngdoc
    -0.90
    featureID
    -0.86
    findpost
    -0.83
     OFDb
    -0.83
    脚注の使い方
    -0.77
    verwijspagina
    -0.75
    UAGES
    -0.73
    endphp
    -0.72
    POSITIVE LOGITS
    p
    0.38
     secteur
    0.36
    nos
    0.34
    b
    0.34
    o
    0.34
    a
    0.33
     care
    0.32
    lit
    0.32
    f
    0.32
    ing
    0.32
    Activations Density 0.144%

    No Known Activations