© 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. 2133
    Prev
    Next
    INDEX
    Explanations

    phrases indicating equivalence or comparison

    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
    abestanden
    -0.83
    PullParser
    -0.81
     createStore
    -0.75
     jadx
    -0.72
     crescita
    -0.68
    Хьажоргаш
    -0.67
    賀状
    -0.67
     يتيمه
    -0.66
    MessageTagHelper
    -0.64
    gdx
    -0.63
    POSITIVE LOGITS
     equivalent
    1.45
     equivalence
    1.40
     Equivalent
    1.36
    Equivalent
    1.34
    equivalent
    1.30
     equivalents
    1.29
    equiv
    1.25
     equival
    1.25
     Equi
    1.24
    equi
    1.23
    Activations Density 0.033%

    No Known Activations