© 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. 19128
    Prev
    Next
    INDEX
    Explanations

    phrases related to job applications and educational contexts

    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
    insee
    -0.52
    bebe
    -0.52
     inu
    -0.51
     Hille
    -0.51
     <<<<<<<<<<<<<<
    -0.50
    findpost
    -0.50
     FetchType
    -0.50
    ########.
    -0.50
    DropColumn
    -0.50
    iram
    -0.49
    POSITIVE LOGITS
    PreferredItem
    0.76
     ujednoznacz
    0.58
     dä
    0.55
    oa̍t
    0.53
    similar
    0.51
     thường
    0.50
    AsUp
    0.48
    same
    0.47
     dieťa
    0.46
    commonly
    0.46
    Activations Density 1.425%

    No Known Activations