© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 0
    Prev
    Next
    INDEX
    Explanations

    conjunctions and relational words that suggest connections or similarities

    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
     Efq
    -1.55
     Jefus
    -1.38
     Majefty
    -1.34
     purpoſe
    -1.31
     ftate
    -1.31
     himſelf
    -1.30
     poffible
    -1.28
     itſelf
    -1.27
     myſelf
    -1.27
     Shakspeare
    -1.26
    POSITIVE LOGITS
     and
    1.44
     And
    1.19
     và
    1.10
     AND
    1.05
    and
    1.03
    /
    0.98
     then
    0.96
     \&
    0.93
     и
    0.93
    Và
    0.92
    Activations Density 2.982%

    No Known Activations