© 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. 16212
    Prev
    Next
    INDEX
    Explanations

    conjunctions used in a context involving relationships or connections

    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
    MigrationBuilder
    -0.71
    WithIOException
    -0.58
     nakalista
    -0.56
    rungsseite
    -0.54
    isière
    -0.54
    #+#
    -0.53
    azin
    -0.52
     flamme
    -0.51
     betweenstory
    -0.51
    ppchen
    -0.51
    POSITIVE LOGITS
    Portail
    0.72
    Portale
    0.58
    JspWriter
    0.57
    BindingResult
    0.50
    vertre
    0.49
    lopen
    0.49
     bureaus
    0.49
    XmlAccessorType
    0.47
    baking
    0.47
     Turnpike
    0.47
    Activations Density 0.226%

    No Known Activations