© 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. 5-CLT-HP
    7. 93055
    Prev
    Next
    INDEX
    Explanations

    Dallas

    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
     fashion
    -0.51
     deaths
    -0.48
     sprzed
    -0.47
    styleUrls
    -0.47
     died
    -0.47
    '
    -0.46
     map
    -0.45
     killed
    -0.44
     death
    -0.42
    NewUrlParser
    -0.42
    POSITIVE LOGITS
     propOrder
    0.83
    Personensuche
    0.79
     Roskov
    0.79
    setVerticalGroup
    0.70
     sẻ
    0.70
    ]")]
    0.69
     autorytatywna
    0.69
    protoimpl
    0.67
     gynhyrchwyd
    0.66
    homonymie
    0.66
    Activations Density 0.009%

    No Known Activations