© 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. 21404
    Prev
    Next
    INDEX
    Explanations

    references to the presence or involvement of people in the context

    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
    glEnd
    -0.78
    ServletException
    -0.75
    WebpackPlugin
    -0.75
    GEBURTSDATUM
    -0.73
    verwijspagina
    -0.72
    glGen
    -0.72
    textSize
    -0.71
    بوابة
    -0.69
    flink
    -0.69
    ]{\
    -0.69
    POSITIVE LOGITS
     OTHERS
    0.73
    Others
    0.72
    others
    0.72
     Others
    0.71
    幼儿
    0.69
     Mich
    0.69
     consenso
    0.69
     επικ
    0.66
     înainte
    0.65
     Kochi
    0.65
    Activations Density 0.011%

    No Known Activations