© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77872
    Prev
    Next
    INDEX
    Explanations

    blood vessels

    np_max-act-logits · 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
     betweenstory
    -0.60
    Dati
    -0.58
     förr
    -0.57
    viewDidLoad
    -0.56
     StatefulWidget
    -0.56
    styleable
    -0.56
    </tfoot>
    -0.55
     Sander
    -0.54
    ErrorListener
    -0.54
     présidenti
    -0.53
    POSITIVE LOGITS
     vessels
    0.77
    Ve
    0.65
     ve
    0.64
     vasi
    0.63
     vessel
    0.61
     blood
    0.60
     ven
    0.59
    cap
    0.59
     Ve
    0.58
     var
    0.57
    Activations Density 0.040%

    No Known Activations