© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1072
    Prev
    Next
    INDEX
    Explanations

    duration/differences

    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
     inappropriés
    -0.68
     units
    -0.66
     Units
    -0.62
    units
    -0.60
     UNITS
    -0.59
     regiments
    -0.59
     specimens
    -0.58
    UNITS
    -0.58
    deed
    -0.57
    Units
    -0.56
    POSITIVE LOGITS
    WriteTagHelper
    0.54
     referrerpolicy
    0.54
    RTLD
    0.53
    msgSender
    0.49
     OkHttpClient
    0.48
    PageRoute
    0.46
    WriteBarrier
    0.46
     Wiktionnaire
    0.46
    AuthProvider
    0.45
     '{@
    0.44
    Activations Density 0.004%

    No Known Activations