© 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. 0-CLT-HP
    7. 999
    Prev
    Next
    INDEX
    Explanations

    dissolved

    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
    rawDesc
    -0.69
     aveug
    -0.69
     Shreve
    -0.69
     humaines
    -0.67
    WriteLiteral
    -0.66
     säll
    -0.66
    ſelf
    -0.64
     relâche
    -0.64
     imprimée
    -0.64
     fondament
    -0.63
    POSITIVE LOGITS
    ers
    0.65
    s
    0.57
    setupUi
    0.55
    IndentedString
    0.54
    GenerationType
    0.52
    y
    0.52
    ChildIndex
    0.51
    omitempty
    0.47
    XmlAccessType
    0.47
    buss
    0.47
    Activations Density 0.042%

    No Known Activations