© 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. 6509
    Prev
    Next
    INDEX
    Explanations

    references to defining or describable states or circumstances

    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
     conditions
    -1.18
     circumstances
    -1.06
     Conditions
    -0.95
    Conditions
    -0.94
    conditions
    -0.93
     CONDITIONS
    -0.87
     Circumstances
    -0.87
     Bedingungen
    -0.73
     условий
    -0.72
     scenarios
    -0.68
    POSITIVE LOGITS
     condition
    1.74
     Condition
    1.68
     CONDITION
    1.66
    condition
    1.55
    Condition
    1.48
    CONDITION
    1.19
     condición
    1.12
     conditioned
    1.11
     Zustand
    1.05
     condição
    1.05
    Activations Density 0.070%

    No Known Activations