© 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. 1316
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that express preference or alternatives

    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
    verständlich
    -0.75
    ModelSerializer
    -0.72
    Rik
    -0.70
     protoimpl
    -0.70
    Oli
    -0.69
    POSIX
    -0.69
     dataGridView
    -0.69
     AttributeSet
    -0.69
    Bil
    -0.68
    modelBuilder
    -0.68
    POSITIVE LOGITS
     Rather
    1.36
    Rather
    1.28
     Instead
    1.27
    uttosto
    1.25
    Instead
    1.23
     rather
    1.22
    instead
    1.18
     instead
    1.16
    rather
    1.13
     plutôt
    0.93
    Activations Density 0.081%

    No Known Activations