Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14624
    Prev
    Next
    INDEX
    Explanations

    references to the action of applying pressure or force by squeezing

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    basicConfig
    -0.65
    modelBuilder
    -0.63
     localObject
    -0.63
     NgModule
    -0.60
    VELAND
    -0.60
    astify
    -0.60
     AttributeSet
    -0.59
    CppMethod
    -0.58
    ExtendWith
    -0.58
    TypedDataSet
    -0.57
    POSITIVE LOGITS
     squeeze
    3.75
     Squeeze
    3.30
     squeezing
    2.92
     squeezed
    2.89
    squeeze
    2.80
     squee
    2.73
    queeze
    2.41
    quee
    1.80
    挤
    1.31
    擠
    1.21
    Activations Density 0.000%

    No Known Activations