© 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. 40342
    Prev
    Next
    INDEX
    Explanations

    assignments or throwing

    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
     stored
    -1.07
     assigned
    -0.98
    stored
    -0.95
     scattata
    -0.91
    assigned
    -0.90
     allocated
    -0.88
     distributed
    -0.88
     quæ
    -0.87
     deployed
    -0.87
     allotted
    -0.85
    POSITIVE LOGITS
    eaky
    0.60
     Dat
    0.50
     ag
    0.48
     parallel
    0.48
     null
    0.48
    allenges
    0.47
    CommonModule
    0.47
     ins
    0.47
    unsch
    0.47
     }^{(
    0.47
    Activations Density 0.139%

    No Known Activations