© 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. 26312
    Prev
    Next
    INDEX
    Explanations

    text that discusses comparisons and evaluations of fashion trends

    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
    <bos>
    -0.68
    Personendaten
    -0.65
    OGND
    -0.62
     CreateTagHelper
    -0.58
     '\\;'
    -0.56
     ویکی‌پدی
    -0.54
    )";
    -0.54
     protoimpl
    -0.53
    PhysRevD
    -0.53
    "—
    -0.52
    POSITIVE LOGITS
    ########.
    0.75
    expandindo
    0.65
    gdx
    0.59
     néglig
    0.56
    윗
    0.56
    DataAnnotations
    0.54
    Hochspringen
    0.54
    ]<=
    0.54
    ặn
    0.54
    bacher
    0.53
    Activations Density 0.206%

    No Known Activations