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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13923
    Prev
    Next
    INDEX
    Explanations

    visual patterns containing a specific geometric structure, such as overlapping horizontal and vertical lines or motifs

    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
     nakalista
    -0.45
    nett
    -0.45
     ET
    -0.44
    ket
    -0.43
    iz
    -0.42
    hov
    -0.42
    nal
    -0.41
     fran
    -0.40
     des
    -0.40
     por
    -0.39
    POSITIVE LOGITS
    WT
    2.22
    tagHelperRunner
    1.10
     doInBackground
    0.95
    EndInit
    0.88
    ########.
    0.84
    KURZBESCHREIBUNG
    0.84
    MLLoader
    0.83
    RemoveField
    0.81
    脚注の使い方
    0.81
     InputDecoration
    0.81
    Activations Density 0.002%

    No Known Activations