© 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. 25357
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and assessments related to hypothetical scenarios

    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
    orus
    -0.51
    fromnode
    -0.51
     doInBackground
    -0.47
    горь
    -0.45
     Corintios
    -0.45
    よろしくお願いいたします
    -0.44
    сет
    -0.44
    ora
    -0.43
    finally
    -0.43
    vaného
    -0.43
    POSITIVE LOGITS
    GHIJKLM
    0.68
    mobileqq
    0.67
     CreateTagHelper
    0.66
    #+#
    0.66
     ujednoznacz
    0.66
    MockBean
    0.63
     disambiguazione
    0.63
    atrième
    0.63
     >=",
    0.62
    ➯
    0.61
    Activations Density 0.269%

    No Known Activations