© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 879
    Prev
    Next
    INDEX
    Explanations

    a word that follows "type of" or precedes a roman numeral

    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/blocks.22.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.22.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
     ISNI
    -0.51
     sağ
    -0.48
    KommentareTeilen
    -0.48
    ต้น
    -0.47
    opencv
    -0.47
    KURZBESCHREIBUNG
    -0.47
    enei
    -0.46
    ampung
    -0.45
     Sequel
    -0.44
     CSRF
    -0.44
    POSITIVE LOGITS
     TextInputType
    0.83
    faces
    0.82
     AssemblyCulture
    0.81
     CreateTagHelper
    0.79
    writers
    0.76
    XmlType
    0.75
     getType
    0.75
    foundland
    0.72
    written
    0.70
     userType
    0.67
    Activations Density 0.480%

    No Known Activations