© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5282
    Prev
    Next
    INDEX
    Explanations

    terms related to medical techniques and comparisons of methodologies

    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
    __':
    -0.89
    "):
    -0.85
    parsedMessage
    -0.81
    '):
    -0.80
    HomeAsUpEnabled
    -0.78
    ]")]
    -0.77
    SaveChangesAsync
    -0.73
    .")
    -0.73
    __":
    -0.71
    "))
    -0.69
    POSITIVE LOGITS
    res
    0.50
    ate
    0.47
    setopt
    0.44
    w
    0.43
    ical
    0.43
    na
    0.43
     She
    0.42
    ana
    0.40
     полу
    0.40
    cur
    0.40
    Activations Density 0.565%

    No Known Activations