© 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. 1-CLT-HP
    4. 13173
    Prev
    Next
    INDEX
    Explanations

    hatched

    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
    ota
    -1.23
     hatched
    -1.10
    OTA
    -0.84
    UserScript
    -0.71
    FormTagHelper
    -0.65
     IBOutlet
    -0.60
    
    -0.59
    MemoryWarning
    -0.58
    AFFIRMED
    -0.58
     xenia
    -0.58
    POSITIVE LOGITS
    i
    0.52
     tarvit
    0.50
    DllImport
    0.49
    Hentet
    0.49
    pug
    0.47
    fen
    0.45
     díg
    0.44
    kton
    0.44
    phe
    0.43
    k
    0.42
    Activations Density 0.038%

    No Known Activations