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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 650
    Prev
    Next
    INDEX
    Explanations

    positive evaluations or descriptors of quality

    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
     itſelf
    -1.02
     myſelf
    -0.98
    hadiran
    -0.95
    InjectAttribute
    -0.89
     Thorne
    -0.86
     Renata
    -0.85
     becauſe
    -0.85
    原始内容存档于
    -0.82
     chofe
    -0.82
     Theſe
    -0.79
    POSITIVE LOGITS
     Good
    1.49
    GOOD
    1.43
     GOOD
    1.42
    Good
    1.41
    good
    1.38
     good
    1.26
     Goodwin
    1.17
     Goodman
    1.13
     Bad
    1.06
    Bad
    1.04
    Activations Density 0.204%

    No Known Activations