© 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. 19151
    Prev
    Next
    INDEX
    Explanations

    references to technology and communication tools

    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
    脚注の使い方
    -1.09
    XmlAccessType
    -0.79
    benhavn
    -0.72
     useContext
    -0.71
    queryInterface
    -0.71
    apatalk
    -0.70
    日閲覧
    -0.69
    RenderAtEndOf
    -0.69
    Чыганаклар
    -0.69
     referrerpolicy
    -0.68
    POSITIVE LOGITS
    Helping
    0.47
     aiut
    0.47
     advise
    0.47
     advises
    0.44
     recomendación
    0.42
     advising
    0.42
    rungsseite
    0.42
     aconse
    0.41
    helping
    0.40
     råd
    0.38
    Activations Density 0.019%

    No Known Activations