© 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. 5805
    Prev
    Next
    INDEX
    Explanations

    concepts related to spirituality and virtuous qualities

    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
    AccessorTable
    -0.87
     transférez
    -0.68
    fjspx
    -0.61
    ISupport
    -0.59
     Innoc
    -0.59
    ReusableCell
    -0.59
    niająca
    -0.58
    tagHelperRunner
    -0.56
    +#+#
    -0.56
    InitVars
    -0.56
    POSITIVE LOGITS
     Photocase
    0.61
    IntoConstraints
    0.54
    idance
    0.52
     pořád
    0.50
    shafen
    0.49
     defaultstate
    0.49
    odotus
    0.48
    lottesville
    0.47
    oliber
    0.47
    lardır
    0.45
    Activations Density 0.213%

    No Known Activations