© 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. 20-CLT-HP
    7. 77504
    Prev
    Next
    INDEX
    Explanations

    inclusion

    np_max-act-logits · 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
    IntoConstraints
    -0.72
    
    -0.57
    RenderAtEndOf
    -0.56
     useHistory
    -0.56
    ])))
    -0.55
    øde
    -0.55
    IVEREF
    -0.52
     entstanden
    -0.51
     BoxDecoration
    -0.50
     distanciation
    -0.49
    POSITIVE LOGITS
     contained
    0.85
     featured
    0.81
    contained
    0.80
     included
    0.73
     possessed
    0.72
     involved
    0.68
     focused
    0.65
    possessed
    0.65
     bore
    0.64
     consisted
    0.64
    Activations Density 0.000%

    No Known Activations