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. 26651
    Prev
    Next
    INDEX
    Explanations

    assertions or claims about the validity of a statement or situation

    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
    BorderFactory
    -0.72
    Дереккөздер
    -0.67
     useRouter
    -0.63
    tagHelperRunner
    -0.63
     myſelf
    -0.59
    expandindo
    -0.58
     quæ
    -0.56
     yoox
    -0.55
     zalando
    -0.54
     Bridgewater
    -0.54
    POSITIVE LOGITS
     JLabel
    0.82
    VersionUID
    0.65
     saites
    0.64
     rues
    0.64
    bura
    0.60
    antMatchers
    0.59
    logram
    0.58
    bnf
    0.58
    ymce
    0.58
    ftagPool
    0.58
    Activations Density 0.028%

    No Known Activations