© 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. 41493
    Prev
    Next
    INDEX
    Explanations

    vessels

    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
     vessel
    -0.60
     tqdm
    -0.60
    </thead>
    -0.57
     htons
    -0.57
     RouterModule
    -0.56
     Vessel
    -0.54
    PhysRevLett
    -0.54
    awtextra
    -0.54
    URIComponent
    -0.53
    vyšší
    -0.53
    POSITIVE LOGITS
    Controllo
    0.63
    niająca
    0.55
     članak
    0.55
    rentices
    0.53
     connections
    0.52
     inhibition
    0.51
    ectoria
    0.51
     auditions
    0.51
    contributions
    0.51
    InitVars
    0.48
    Activations Density 0.379%

    No Known Activations