© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16765
    Prev
    Next
    INDEX
    Explanations

    terms related to Dark Matter and its properties in the context of particle physics and astrophysics

    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
    InjectAttribute
    -0.70
    SPATH
    -0.69
    انجليز
    -0.68
    wieś
    -0.63
    ंदीखरीदारी
    -0.63
    IGraphics
    -0.63
    
    -0.61
     initComponents
    -0.61
    oa̍t
    -0.60
    Collegamenti
    -0.59
    POSITIVE LOGITS
    anteil
    0.56
    surate
    0.56
     ';
    0.55
    projected
    0.53
    Kira
    0.51
    enquête
    0.51
     imageNamed
    0.50
     comportement
    0.49
    več
    0.48
     ADVIS
    0.48
    Activations Density 0.010%

    No Known Activations