Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 65
    Prev
    Next
    INDEX
    Explanations

    phrases contrasting ideas or conditions

    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
     myſelf
    -0.90
     Shakspeare
    -0.90
     Roskov
    -0.85
     Majefty
    -0.84
     Efq
    -0.84
    ſelf
    -0.83
     Monfieur
    -0.83
     Jefus
    -0.81
     Pliny
    -0.79
     uric
    -0.78
    POSITIVE LOGITS
     But
    1.79
     but
    1.68
    But
    1.51
    but
    1.42
     BUT
    1.34
     yet
    1.30
     pero
    1.23
     nevertheless
    1.16
     Yet
    1.13
    BUT
    1.13
    Activations Density 1.456%

    No Known Activations