© 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. 18-RES-MATRYOSHKA-DC
    7. 1333
    Prev
    Next
    INDEX
    Explanations

    clauses using conditional words like "if", "then", and "unless"

    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.18.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.18.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
    ことができました
    -0.52
    limus
    -0.52
     मैंने
    -0.51
     lẫn
    -0.49
    ことにしました
    -0.49
     myself
    -0.49
    סף
    -0.47
    сар
    -0.46
     نے
    -0.46
    tonsoft
    -0.46
    POSITIVE LOGITS
     then
    1.44
     entonces
    1.16
     allora
    1.09
    then
    1.09
     thì
    1.08
     THEN
    1.05
     Then
    0.98
    则
    0.95
    Then
    0.93
    THEN
    0.92
    Activations Density 1.139%

    No Known Activations