© 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. 12-RES-MATRYOSHKA-DC
    7. 9739
    Prev
    Next
    INDEX
    Explanations

    terms related to suspension or the act of being suspended

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (';
    -0.78
    évaluateur
    -0.76
    Goa
    -0.75
     Atkinson
    -0.75
    (',');
    -0.75
     Catto
    -0.75
     veneta
    -0.73
    +'</
    -0.72
     RTC
    -0.71
    Holt
    -0.71
    POSITIVE LOGITS
     suspend
    1.17
     suspensions
    1.17
     suspension
    1.05
     Suspension
    1.02
     Sus
    1.00
    Suspend
    1.00
    suspend
    0.95
     SUSP
    0.94
     suspended
    0.93
     suspens
    0.93
    Activations Density 0.015%

    No Known Activations