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. 44659
    Prev
    Next
    INDEX
    Explanations

    venue

    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
    enzie
    -0.71
    HEET
    -0.61
    ATHY
    -0.60
     dest
    -0.59
    street
    -0.59
    ffon
    -0.57
    YSTAL
    -0.57
     destination
    -0.57
    destination
    -0.57
    hops
    -0.56
    POSITIVE LOGITS
    ArrowToggle
    0.62
     '\\;'
    0.61
    μφωνα
    0.59
    AnchorStyles
    0.58
    ViewFeatures
    0.58
     handleMessage
    0.58
    tagHelperRunner
    0.57
     متعلقه
    0.55
    下手
    0.54
     Winaray
    0.53
    Activations Density 1.478%

    No Known Activations