© 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. 92094
    Prev
    Next
    INDEX
    Explanations

    access

    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
    Personendaten
    -1.08
     access
    -0.85
    access
    -0.77
     acceso
    -0.75
     للمعارف
    -0.73
     Access
    -0.72
    Access
    -0.71
    ACCESS
    -0.67
     accès
    -0.67
     referenties
    -0.66
    POSITIVE LOGITS
    TagMode
    0.64
     point
    0.56
     paths
    0.55
     path
    0.53
     chan
    0.52
    ()].
    0.49
     PLA
    0.48
    Imported
    0.48
     points
    0.47
     paradigms
    0.47
    Activations Density 0.069%

    No Known Activations