© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14830
    Prev
    Next
    INDEX
    Explanations

    references to a specific positive rating or ability score

    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
    //
    -0.93
    WriteTagHelper
    -0.91
     resourceCulture
    -0.90
     GenerationType
    -0.77
     lenker
    -0.73
     فريبيس
    -0.72
    SequentialGroup
    -0.70
    /**
    -0.69
    PreInfinity
    -0.68
    featureID
    -0.67
    POSITIVE LOGITS
    rose
    2.08
    eable
    1.32
    ROSE
    1.02
    roses
    0.82
    Халык
    0.52
    ATURES
    0.50
    simile
    0.49
    Quar
    0.45
    celli
    0.44
     postre
    0.44
    Activations Density 0.005%

    No Known Activations