© 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. 3538
    Prev
    Next
    INDEX
    Explanations

    career

    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
     Bescheid
    -0.56
     typical
    -0.52
    strophic
    -0.52
     flying
    -0.52
    yelitis
    -0.50
    κτηρισ
    -0.50
     thác
    -0.49
     driving
    -0.49
    Continuar
    -0.49
    показания
    -0.49
    POSITIVE LOGITS
    DebuggerNonUser
    0.52
    SequentialGroup
    0.48
    "])
    0.48
    AlterField
    0.47
    UnusedPrivate
    0.46
    __':
    0.45
    Portale
    0.45
     pinulongan
    0.45
    cca
    0.44
     sì
    0.44
    Activations Density 0.022%

    No Known Activations