© 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. 13382
    Prev
    Next
    INDEX
    Explanations

    references to a specific software package or component, often involving "kit" and related terms

    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
    Kit
    -1.82
     Kit
    -1.22
    KIT
    -0.75
     صوتيه
    -0.71
     Audiodateien
    -0.66
    Datuak
    -0.63
    +:+
    -0.63
    InstrumentedTest
    -0.61
    ApiProperty
    -0.61
    openConnection
    -0.61
    POSITIVE LOGITS
     kit
    1.20
     kits
    0.72
    ñora
    0.56
    EndContext
    0.54
    ledem
    0.54
     Fiche
    0.53
    Demografie
    0.53
     toolkit
    0.52
    Bernie
    0.52
     kiti
    0.52
    Activations Density 0.004%

    No Known Activations