Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 14957
    Prev
    Next
    INDEX
    Explanations

    phrases that express emotional connections or sentiments

    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
     Monfieur
    -0.80
    ⓧ
    -0.77
     Huguen
    -0.71
     CreateTagHelper
    -0.69
     Infór
    -0.69
     '\\;'
    -0.69
    下载附件
    -0.69
    NewUrlParser
    -0.69
    ;->
    -0.68
     pinulongan
    -0.67
    POSITIVE LOGITS
     intra
    0.54
    ValueStyle
    0.51
     Schmidt
    0.49
    mell
    0.44
    ,
    0.44
     Sal
    0.44
    irat
    0.44
     co
    0.43
    transQ
    0.43
     sal
    0.43
    Activations Density 0.020%

    No Known Activations