© 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. 22520
    Prev
    Next
    INDEX
    Explanations

    elements related to text processing and visual display in languages

    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
     soutenu
    -0.47
     dirigió
    -0.47
    arna
    -0.42
     Colombie
    -0.41
    $(
    -0.41
    mators
    -0.40
    WriteLiteral
    -0.40
    MockMvc
    -0.40
     dipl
    -0.38
    lagio
    -0.38
    POSITIVE LOGITS
    fjspx
    0.75
     combineReducers
    0.74
    UnsafeEnabled
    0.74
    Бахар
    0.72
     BoxFit
    0.72
     NUKAT
    0.71
    NewUrlParser
    0.70
    CPtr
    0.69
     wireType
    0.67
    phemy
    0.67
    Activations Density 0.002%

    No Known Activations