© 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. 1008
    Prev
    Next
    INDEX
    Explanations

    August

    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
    ed
    -0.68
    enumii
    -0.50
    ised
    -0.50
    EST
    -0.43
    ized
    -0.43
    GRANTED
    -0.42
    TagHelper
    -0.42
    item
    -0.42
     IBOutlet
    -0.42
     UITableView
    -0.41
    POSITIVE LOGITS
    inian
    0.66
    SharedDtor
    0.62
    inians
    0.60
    XmlAccessType
    0.56
    inus
    0.56
    WebElementEntity
    0.56
    inos
    0.55
    אות
    0.54
    inas
    0.53
    onian
    0.52
    Activations Density 0.001%

    No Known Activations