© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 28623
    Prev
    Next
    INDEX
    Explanations

    terms related to the Proto family and its derivatives in scientific 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
    alamus
    -0.83
    stdlib
    -0.82
    ppins
    -0.79
    VOL
    -0.75
     hee
    -0.75
    HomeAsUpEnabled
    -0.74
    Архівовано
    -0.74
    DateField
    -0.74
    ModelAdmin
    -0.73
     Gees
    -0.73
    POSITIVE LOGITS
     proto
    1.43
     Proto
    1.42
    proto
    1.41
     prototypes
    1.36
    Proto
    1.27
    PROTO
    1.21
     prototyping
    1.19
     PROTO
    1.16
     prototype
    1.13
     Prototype
    1.11
    Activations Density 0.013%

    No Known Activations