© 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. 23460
    Prev
    Next
    INDEX
    Explanations

    terms related to condensation processes

    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
    Negative Logits
     VIAF
    -0.79
     Archie
    -0.66
     Jocelyn
    -0.65
     REPORTER
    -0.65
    vVar
    -0.63
    VIAF
    -0.63
    ポーター
    -0.60
     Rote
    -0.60
     Whelan
    -0.60
     cren
    -0.59
    POSITIVE LOGITS
     Condens
    1.58
     condens
    1.47
     condensation
    1.41
     condense
    1.38
    densed
    1.37
     condensed
    1.30
     Cond
    1.25
     condensate
    1.23
     condensing
    1.23
     Condensed
    1.19
    Activations Density 0.013%

    No Known Activations