© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26600
    Prev
    Next
    INDEX
    Explanations

    expressions of personal thoughts or beliefs

    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
     Thought
    -1.13
    thought
    -1.08
     thought
    -1.05
    Thought
    -0.99
     THOUGHT
    -0.99
    脚注の使い方
    -0.89
     ſen
    -0.84
     ſmall
    -0.84
     pensato
    -0.83
     ſtate
    -0.82
    POSITIVE LOGITS
    malink
    0.58
    irms
    0.56
    ssa
    0.56
     mẽ
    0.56
    enderror
    0.52
     Kaur
    0.51
    iscus
    0.50
    breakpoints
    0.49
    assem
    0.47
     Bess
    0.47
    Activations Density 0.015%

    No Known Activations