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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16236
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating involvement or relationships in research 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
    Portale
    -1.02
     للمعارف
    -0.98
     MonoBehaviour
    -0.93
    QMetaType
    -0.88
    yntaxException
    -0.88
    InitStruct
    -0.83
    endpush
    -0.83
    Portail
    -0.81
    \{\\
    -0.79
    httphttps
    -0.79
    POSITIVE LOGITS
     this
    0.54
     accordingly
    0.54
     both
    0.53
     demonstrated
    0.48
    kaitan
    0.47
     each
    0.47
     indicated
    0.47
    tvrt
    0.47
     nép
    0.46
     several
    0.46
    Activations Density 0.195%

    No Known Activations