© 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. 6551
    Prev
    Next
    INDEX
    Explanations

    references to suspension or suspended states

    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
    Assad
    -0.63
    ornment
    -0.61
    (',');
    -0.59
    writeFieldEnd
    -0.59
     Catto
    -0.57
     certiorari
    -0.57
    SPATH
    -0.56
    ThroughAttribute
    -0.56
     Kanna
    -0.55
    ోగ
    -0.55
    POSITIVE LOGITS
     suspension
    3.22
     suspended
    3.03
     suspend
    2.94
     Suspension
    2.91
     suspensions
    2.83
    suspension
    2.77
     Suspended
    2.73
    Suspension
    2.73
    suspended
    2.73
     SUSP
    2.72
    Activations Density 0.041%

    No Known Activations