© 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. 12-RES-MATRYOSHKA-DC
    7. 255
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or clauses indicating uncertainty or hypothetical situations

    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
     reise
    -0.68
    jdt
    -0.63
     ambass
    -0.61
     stap
    -0.59
     rozs
    -0.59
     PLA
    -0.58
    PLA
    -0.57
    meiras
    -0.57
    lardır
    -0.57
    wright
    -0.56
    POSITIVE LOGITS
     if
    1.49
     If
    1.34
    if
    1.27
    If
    1.25
    żeli
    1.22
    Nếu
    1.22
    إذا
    1.20
     IF
    1.19
    หาก
    1.13
    Якщо
    1.08
    Activations Density 0.870%

    No Known Activations