© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91919
    Prev
    Next
    INDEX
    Explanations

    ac

    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
     ac
    -1.68
     AC
    -1.56
     Ac
    -1.55
    Ac
    -1.51
    AC
    -1.35
     acc
    -1.27
    ac
    -1.27
    Acc
    -1.01
    acc
    -0.97
     acco
    -0.96
    POSITIVE LOGITS
     manqué
    0.65
     ddelweddau
    0.64
    Obrázky
    0.63
    IUrlHelper
    0.60
    uate
    0.60
     linkovi
    0.59
    jandro
    0.58
     AssemblyTitle
    0.57
     @"/
    0.56
     doubtnut
    0.56
    Activations Density 0.090%

    No Known Activations