© 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. 12-RES-MATRYOSHKA-DC
    7. 19652
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or relevance in various contexts

    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
    󠁢
    -0.48
     Advance
    -0.46
     étrang
    -0.45
    holms
    -0.44
    ioca
    -0.44
    नलिखित
    -0.43
    clara
    -0.43
    AppCompatTheme
    -0.43
     aucune
    -0.42
     Taktlose
    -0.42
    POSITIVE LOGITS
     וגם
    0.71
     дописавши
    0.70
    XmlAccessorType
    0.63
    RRect
    0.63
    gså
    0.61
    êques
    0.60
    SerializedName
    0.59
    GeneratedCode
    0.59
    ApiModelProperty
    0.59
    CodeAttribute
    0.58
    Activations Density 0.214%

    No Known Activations