© 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. 3-RES-MATRYOSHKA-DC
    7. 2541
    Prev
    Next
    INDEX
    Explanations

    the word "suspended" and related forms.

    oai_token-act-pair · gemini-2.0-flash
    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
    (',');
    -0.68
    évaluateur
    -0.65
    teborg
    -0.64
     apellidos
    -0.64
     koti
    -0.61
     Polskiego
    -0.61
     Utica
    -0.60
     Olson
    -0.59
     Catto
    -0.59
     Gallimard
    -0.59
    POSITIVE LOGITS
     suspended
    2.80
     suspend
    2.69
     suspension
    2.64
     Suspended
    2.55
    suspended
    2.55
     Suspension
    2.42
     suspending
    2.42
    Suspended
    2.36
    suspension
    2.34
    Suspension
    2.31
    Activations Density 0.075%

    No Known Activations