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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 60
    Prev
    Next
    INDEX
    Explanations

    phrases related to notable discoveries or revelations

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.64
     ELSE
    -0.45
    λαν
    -0.45
    󠁢
    -0.45
     continuant
    -0.44
     Tent
    -0.44
    disambiguation
    -0.43
     exception
    -0.43
    ophone
    -0.43
    zola
    -0.42
    POSITIVE LOGITS
    <bos>
    3.13
     itſelf
    0.60
    __':
    
    0.60
    /**
    0.57
    __":
    
    0.56
    #
    0.54
     raiſ
    0.53
    /*
    0.52
     the
    0.52
    //
    0.51
    Activations Density 94.247%

    No Known Activations