© 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. 2-RES-MATRYOSHKA-DC
    7. 4777
    Prev
    Next
    INDEX
    Explanations

    references to specific types or instances of tracks or railway segments

    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
    Ra
    -0.88
     ra
    -0.81
     Ra
    -0.77
    ra
    -0.76
    RA
    -0.76
     RA
    -0.65
    তথ্যসূত্র
    -0.61
     Telerik
    -0.60
     maiden
    -0.59
     Lovato
    -0.59
    POSITIVE LOGITS
     track
    3.67
     Track
    3.56
    Track
    3.39
    track
    3.30
     TRACK
    3.23
     tracks
    3.02
    TRACK
    2.95
     Tracks
    2.81
    tracks
    2.67
    Tracks
    2.59
    Activations Density 0.119%

    No Known Activations