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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3155
    Prev
    Next
    INDEX
    Explanations

    by

    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
    HasAnnotation
    -0.57
     wikipagina
    -0.55
     colgantes
    -0.53
    rivit
    -0.52
     málaga
    -0.52
     ordinaires
    -0.51
     détach
    -0.50
     prochaines
    -0.50
     étrang
    -0.50
    ัตร
    -0.49
    POSITIVE LOGITS
     excited
    0.61
     determined
    0.60
     eager
    0.59
     impatient
    0.55
     hungry
    0.55
    ]--;
    0.55
     diligent
    0.54
     concerned
    0.54
     enthusiastic
    0.53
     brave
    0.52
    Activations Density 0.004%

    No Known Activations