© 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. 28654
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presentation and examination of evidence

    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
    apimachinery
    -0.69
    UIControlState
    -0.65
     tslint
    -0.61
    SqlClient
    -0.60
    RegistryLite
    -0.60
     mxArray
    -0.59
     SqlConnection
    -0.58
    nextProps
    -0.58
    Assertion
    -0.58
    الحياه
    -0.58
    POSITIVE LOGITS
    goku
    0.55
    >({
    0.48
    oucí
    0.46
     iconTwitter
    0.45
     QtGui
    0.45
    imler
    0.44
     Comunidad
    0.44
    pegno
    0.44
     bezeichneter
    0.43
    SharedDtor
    0.43
    Activations Density 0.085%

    No Known Activations