© 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. 0-CLT-HP
    7. 41239
    Prev
    Next
    INDEX
    Explanations

    progress

    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
     progress
    -1.56
     Progress
    -1.43
     PROGRESS
    -1.28
    Progress
    -1.23
    progress
    -1.20
     progreso
    -1.05
     progresses
    -0.96
    PROGRESS
    -0.91
     advance
    -0.85
     progrès
    -0.84
    POSITIVE LOGITS
    ➟
    0.60
     itſelf
    0.51
     cliquez
    0.50
     leggere
    0.49
    ]=>
    0.48
     pédagog
    0.46
    Ранее
    0.45
    its
    0.44
    })));
    0.44
     käs
    0.44
    Activations Density 0.034%

    No Known Activations