© 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. 28234
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of 'some' or indefinite quantities

    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
    Someone
    -0.54
    程度上
    -0.47
     sometimes
    -0.46
     diritto
    -0.45
    Somewhere
    -0.45
    -
    -0.44
    sometimes
    -0.44
     sommige
    -0.43
     někdo
    -0.43
    edish
    -0.43
    POSITIVE LOGITS
    AndEndTag
    1.05
    TemporalType
    0.94
     виправивши
    0.89
    ectoria
    0.86
    adaptiveStyles
    0.84
    Cyfeiriadau
    0.84
     CreateTagHelper
    0.81
    PreInfinity
    0.81
     AssemblyTitle
    0.76
    ɵɵ
    0.76
    Activations Density 0.037%

    No Known Activations