© 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. 14150
    Prev
    Next
    INDEX
    Explanations

    terms related to ordinal rankings

    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
    ########.
    -0.69
     BoxDecoration
    -0.67
     Administrativna
    -0.59
     ligiloj
    -0.58
     HasFactory
    -0.55
     Wiktionnaire
    -0.55
    onedDateTime
    -0.53
    发表于
    -0.52
     Houſe
    -0.51
    لينكات
    -0.49
    POSITIVE LOGITS
     ComVisible
    0.75
    RegistryLite
    0.75
    PasswordField
    0.66
     cref
    0.61
    ContentAsync
    0.60
     dàng
    0.59
    يميديا
    0.59
     flames
    0.57
    脚注の使い方
    0.57
    DrawerLayout
    0.57
    Activations Density 0.006%

    No Known Activations