© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10154
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency and typicality of patterns, specifically in language and communication

    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
    ///</
    -0.67
    دانشنامهٔ
    -0.54
    SequentialGroup
    -0.51
     impact
    -0.50
    OOTDTY
    -0.49
    ubei
    -0.49
    zyż
    -0.48
     impacts
    -0.48
    ziare
    -0.47
     Helf
    -0.47
    POSITIVE LOGITS
     المعيارى
    0.63
    SharedDtor
    0.61
     onPage
    0.59
     useRouter
    0.58
    Referències
    0.56
     ISNI
    0.56
    zzleHttp
    0.55
     שוליים
    0.54
    CopyWith
    0.53
    +#+#
    0.52
    Activations Density 0.217%

    No Known Activations