© 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. 10831
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and gatherings

    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
     synthèse
    -0.47
    =/
    -0.47
     мной
    -0.47
     négoci
    -0.47
    operator
    -0.46
     légiti
    -0.45
     marins
    -0.44
    oredCriteria
    -0.44
     Schles
    -0.43
     commerciaux
    -0.43
    POSITIVE LOGITS
     الحره
    0.93
    MIDDLEWARE
    0.69
    enfone
    0.69
     CallOverrides
    0.68
     RSVP
    0.66
     aunts
    0.65
     cousins
    0.64
    IUrlHelper
    0.64
    Kariera
    0.63
    DeleteBehavior
    0.63
    Activations Density 0.098%

    No Known Activations