© 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. 5520
    Prev
    Next
    INDEX
    Explanations

    dialogue and expressions of inquiry or surprise

    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
     doInBackground
    -0.70
     whor
    -0.61
     quæ
    -0.60
     recommandons
    -0.59
     klara
    -0.57
     pyrolysis
    -0.57
    ImageContext
    -0.56
    Còn
    -0.55
     varandra
    -0.53
     metropolitana
    -0.52
    POSITIVE LOGITS
     invokingState
    0.84
     समीक्षक
    0.73
     AssemblyTitle
    0.72
     EconPapers
    0.71
    ]")]
    0.69
    TargetException
    0.67
    쁜
    0.65
    __':
    0.64
    mogorov
    0.63
    WithIOException
    0.61
    Activations Density 0.026%

    No Known Activations