© 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. 0-CLT-HP
    7. 42303
    Prev
    Next
    INDEX
    Explanations

    competent, potent

    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
    Chham
    -0.57
    ceiro
    -0.45
    ItemBackground
    -0.45
     competent
    -0.45
     potent
    -0.42
     competente
    -0.41
     forcé
    -0.41
    Демографія
    -0.40
    Välislingid
    -0.40
     Jesucristo
    -0.40
    POSITIVE LOGITS
     GenerationType
    0.69
    nesc
    0.68
    
    0.66
    Personendaten
    0.65
    ImageContext
    0.63
    HostException
    0.63
     cref
    0.62
    vola
    0.60
    ########.
    0.60
     resourceCulture
    0.59
    Activations Density 0.160%

    No Known Activations