© 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. 91079
    Prev
    Next
    INDEX
    Explanations

    Fifth Amendment, numbered items

    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
    theless
    -0.71
    tures
    -0.68
     stocks
    -0.57
     nhàng
    -0.55
    titions
    -0.53
    ances
    -0.52
    ñales
    -0.51
    able
    -0.50
    ised
    -0.50
    men
    -0.49
    POSITIVE LOGITS
    WebServlet
    0.74
    EndContext
    0.68
    TestingModule
    0.64
    LikeLiked
    0.58
    reportWebVitals
    0.57
    NamedQueries
    0.53
    abestanden
    0.52
     getItemId
    0.51
     Double
    0.50
    awtextra
    0.50
    Activations Density 0.151%

    No Known Activations