© 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. 5711
    Prev
    Next
    INDEX
    Explanations

    phrases indicating discrepancies or contradictions in statements

    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
    AndroidJUnit
    -0.58
    uxxxx
    -0.57
    المشاركات
    -0.56
     preocupes
    -0.56
     trajets
    -0.53
     ComVisible
    -0.52
    openzeppelin
    -0.49
     contextLoads
    -0.49
     تضيفلها
    -0.48
     imagina
    -0.46
    POSITIVE LOGITS
     contradic
    1.09
     contradictory
    1.08
     conflicting
    1.07
     contradicted
    0.98
     contradicts
    0.93
     contradict
    0.86
     contradiction
    0.83
     inconsistent
    0.81
     inconsistency
    0.78
     contradictions
    0.74
    Activations Density 0.543%

    No Known Activations