© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24189
    Prev
    Next
    INDEX
    Explanations

    phrases related to chemical properties and reactions

    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
    ,
    -0.65
     it
    -0.58
     they
    -0.57
     however
    -0.57
     but
    -0.52
     then
    -0.52
    ;
    -0.51
     you
    -0.50
     there
    -0.50
     infierno
    -0.49
    POSITIVE LOGITS
    RectangleBorder
    0.91
    rungsseite
    0.91
     يتيمه
    0.80
     myſelf
    0.80
     snippetHide
    0.77
     محفوظة
    0.74
    HostException
    0.74
     []:
    0.72
    writerow
    0.72
     autorytatywna
    0.70
    Activations Density 0.098%

    No Known Activations