© 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-RES-MATRYOSHKA-DC
    7. 12848
    Prev
    Next
    INDEX
    Explanations

    rows of separator lines with consistent length

    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
    -----------
    -1.40
    ---------
    -0.85
    Personendaten
    -0.61
     resourceCulture
    -0.60
    fromnode
    -0.59
    SequentialGroup
    -0.56
     ----------
    -0.54
    gridx
    -0.54
    Karriere
    -0.52
     Walkover
    -0.52
    POSITIVE LOGITS
    ----------
    1.15
     purpoſe
    1.00
     myſelf
    0.99
     pleaſure
    0.94
     houſe
    0.92
     whoſe
    0.92
     Majefty
    0.90
     ſeveral
    0.90
     itſelf
    0.90
     greateſt
    0.90
    Activations Density 0.002%

    No Known Activations