© 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. 8724
    Prev
    Next
    INDEX
    Explanations

    the conjunction 'and' in various 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
    ivably
    -0.60
    onAttach
    -0.59
    Portale
    -0.57
     babak
    -0.56
    FieldOffset
    -0.56
    μφωνα
    -0.56
    ostante
    -0.56
     ahogy
    -0.54
    ifred
    -0.54
    dataclass
    -0.52
    POSITIVE LOGITS
     propOrder
    0.60
    >{@
    0.57
     interrogation
    0.56
    wahati
    0.52
     MOQ
    0.51
    Geplaatst
    0.50
     mustered
    0.49
    jooq
    0.48
    ViewFeatures
    0.48
     Weak
    0.48
    Activations Density 0.092%

    No Known Activations