© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2815
    Prev
    Next
    INDEX
    Explanations

    on

    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
    NamedQueries
    -0.51
    Jegyzetek
    -0.48
    uitable
    -0.44
     rencontr
    -0.43
    Normdaten
    -0.42
    }?>
    -0.41
    ycz
    -0.40
    ToUpdate
    -0.40
     sonriendo
    -0.40
    nologies
    -0.39
    POSITIVE LOGITS
     responsibility
    1.07
    responsibility
    0.86
     propOrder
    0.84
     respon
    0.81
     Responsibility
    0.81
    Responsibility
    0.75
     roles
    0.73
     leadership
    0.73
     duties
    0.69
     ownership
    0.67
    Activations Density 0.020%

    No Known Activations