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. 10099
    Prev
    Next
    INDEX
    Explanations

    references to reality and its various interpretations or implications

    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
    Alban
    -0.65
    idopsis
    -0.63
     bacter
    -0.58
     polizia
    -0.58
     Aufs
    -0.57
    gets
    -0.57
     aastal
    -0.57
    TabIndex
    -0.57
     المعيارى
    -0.56
    idigung
    -0.56
    POSITIVE LOGITS
     Reality
    1.31
    Reality
    1.23
     reality
    1.16
     realities
    1.16
    reality
    1.05
    )";
    
    0.96
    SpringBootTest
    0.89
     realty
    0.85
     iſt
    0.83
     poffible
    0.83
    Activations Density 0.005%

    No Known Activations