© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93489
    Prev
    Next
    INDEX
    Explanations

    high

    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
     pediatric
    -0.52
    ediat
    -0.50
     الاطلاع
    -0.49
     sociale
    -0.48
     sociaux
    -0.48
     Pediatric
    -0.47
    tidal
    -0.47
     CLINICAL
    -0.47
     Baillargeon
    -0.47
     clinical
    -0.46
    POSITIVE LOGITS
    posedge
    0.71
    passes
    0.70
    pass
    0.63
     contextLoads
    0.61
    PMailer
    0.59
     WaitForSeconds
    0.58
    ądź
    0.57
    ])):
    0.56
    PasswordEncoder
    0.55
     pass
    0.55
    Activations Density 0.398%

    No Known Activations