© 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. 19536
    Prev
    Next
    INDEX
    Explanations

    sentiments of shared experiences and connections among individuals

    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
    Ứ
    -0.45
    pox
    -0.45
    estable
    -0.43
     fast
    -0.42
    new
    -0.42
    λό
    -0.41
    ficiencia
    -0.40
    to
    -0.40
    תו
    -0.39
     civili
    -0.39
    POSITIVE LOGITS
    InjectAttribute
    0.92
     &___
    0.92
    ThroughAttribute
    0.90
     ModelExpression
    0.88
    日閲覧
    0.88
    ScopeManager
    0.87
    enumii
    0.84
     ExecuteAsync
    0.83
    сылкі
    0.83
    RenderAtEndOf
    0.83
    Activations Density 0.092%

    No Known Activations