© 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. 11674
    Prev
    Next
    INDEX
    Explanations

    terms related to energy ejection and explosive events

    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
    Personensuche
    -0.85
     Réponses
    -0.77
    CrossRef
    -0.66
    Enllaces
    -0.65
    Composable
    -0.65
     CreateTagHelper
    -0.64
     disambiguazione
    -0.64
    }}}}
    -0.63
     Normdatei
    -0.63
    IsMutable
    -0.62
    POSITIVE LOGITS
     ejection
    1.29
     ejected
    1.21
     eject
    1.20
     ejec
    0.79
    jection
    0.78
     ejac
    0.73
    voi
    0.72
     expel
    0.69
    jec
    0.67
     Legion
    0.66
    Activations Density 0.026%

    No Known Activations