© 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. 19358
    Prev
    Next
    INDEX
    Explanations

    references to various techniques and methodologies in a scientific or technical context

    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
    s
    -0.82
    h
    -0.81
     Technical
    -0.78
    Technical
    -0.78
     H
    -0.77
    r
    -0.74
     technical
    -0.73
     LOG
    -0.71
    der
    -0.69
    H
    -0.69
    POSITIVE LOGITS
     pleaſure
    1.23
     Forumite
    1.20
     itſelf
    1.17
     Monfieur
    1.17
     Techniques
    1.13
     Majefty
    1.13
     étoient
    1.13
     raiſ
    1.09
     techniques
    1.06
     ſeveral
    1.06
    Activations Density 0.014%

    No Known Activations