© 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. 0-CLT-HP
    7. 90560
    Prev
    Next
    INDEX
    Explanations

    feedback

    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
     returned
    -0.83
    returned
    -0.66
     Feedback
    -0.60
    feedback
    -0.59
    Returned
    -0.56
     Returned
    -0.56
     feedback
    -0.53
     regresó
    -0.51
    rítica
    -0.50
     retour
    -0.49
    POSITIVE LOGITS
     الرياضيه
    0.81
    ized
    0.68
    InstanceState
    0.68
     JpaRepository
    0.67
    ian
    0.61
     Valera
    0.61
    ity
    0.60
    PerformLayout
    0.60
    contentLoaded
    0.60
    ist
    0.59
    Activations Density 0.367%

    No Known Activations