© 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. 2-RES-MATRYOSHKA-DC
    7. 5784
    Prev
    Next
    INDEX
    Explanations

    references to the maximum value or the highest possible level

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incomplète
    -0.73
    Max
    -0.69
     Max
    -0.68
    max
    -0.66
    LookAnd
    -0.66
    Complete
    -0.65
    aarrggbb
    -0.64
     дописавши
    -0.63
     chronograph
    -0.60
    マックス
    -0.60
    POSITIVE LOGITS
     maximum
    1.26
    maximum
    1.11
     Maximum
    1.02
    Maximum
    0.91
     máxima
    0.85
     MAXIMUM
    0.85
     massima
    0.84
     maximale
    0.84
    MAXIMUM
    0.77
     maksimum
    0.70
    Activations Density 0.012%

    No Known Activations