© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 145
    Prev
    Next
    INDEX
    Explanations

    numerical values and their occurrences in contexts that may relate to documentation or references

    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
    ⓧ
    -1.13
    protoimpl
    -1.07
    tvguidetime
    -1.03
    bootstrapcdn
    -1.02
    EndContext
    -1.02
    +#+#
    -0.98
     HasFactory
    -0.97
     Мексичка
    -0.96
     Chwiliwch
    -0.96
    AutoScale
    -0.94
    POSITIVE LOGITS
     
    0.54
     void
    0.45
     all
    0.43
     “
    0.40
     OR
    0.39
     "
    0.38
     under
    0.37
     «
    0.37
     ‘
    0.36
     Cos
    0.36
    Activations Density 1.648%

    No Known Activations