© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 29997
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people

    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
    CppCodeGen
    -0.74
    oredCriteria
    -0.71
     estimés
    -0.71
     تضيفلها
    -0.69
    出版年
    -0.68
     فريبيس
    -0.62
    styleType
    -0.60
    WebVitals
    -0.59
     Pilate
    -0.58
    новниш
    -0.58
    POSITIVE LOGITS
    <eos>
    0.57
    frastructure
    0.57
     […]
    0.56
    ceptre
    0.54
    lecular
    0.53
    ---*/
    0.53
    galus
    0.52
    AttributeSet
    0.50
    implementation
    0.50
     Audiodateien
    0.49
    Activations Density 0.081%

    No Known Activations