© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 11082
    Prev
    Next
    INDEX
    Explanations

    instructions and protocols related to experimental methods

    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
    _));
    -0.52
    ]._
    -0.46
     стату
    -0.44
    чева
    -0.44
    isional
    -0.44
    blem
    -0.44
     Qian
    -0.44
    angor
    -0.43
    ː
    -0.42
    UnitTesting
    -0.42
    POSITIVE LOGITS
     instructions
    1.13
     Instructions
    0.99
     INSTRUCTIONS
    0.99
    instructions
    0.98
    Instructions
    0.96
     instruction
    0.89
     istruzioni
    0.87
     Anleitung
    0.86
     instrucciones
    0.83
     Instruction
    0.82
    Activations Density 0.201%

    No Known Activations