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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24269
    Prev
    Next
    INDEX
    Explanations

    references to visual elements or images in a document

    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
     صوتيه
    -0.63
    makeConstraints
    -0.60
    ]:
    -0.58
    []):
    -0.56
     Fig
    -0.54
    setVerticalGroup
    -0.54
    TemporalType
    -0.54
     fieldNum
    -0.53
    SequentialGroup
    -0.52
    ioutil
    -0.51
    POSITIVE LOGITS
     itſelf
    0.91
     uſe
    0.68
     themſelves
    0.64
    دانشنامهٔ
    0.63
     pleaſure
    0.61
     EPO
    0.60
     ſever
    0.60
     contextLoads
    0.59
     fevere
    0.58
     Finns
    0.58
    Activations Density 0.045%

    No Known Activations