© 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. 12355
    Prev
    Next
    INDEX
    Explanations

    specific locations and measurements related to objects or subjects

    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
    AndEndTag
    -0.65
    oredCriteria
    -0.59
    ftagPool
    -0.55
    __":
    -0.53
    setDo
    -0.52
    DataAnnotations
    -0.50
    ailangan
    -0.49
     CreateTagHelper
    -0.49
    mybatisplus
    -0.44
     vPvB
    -0.44
    POSITIVE LOGITS
     BoxFit
    0.69
    #+#
    0.66
     δὲ
    0.62
     divides
    0.59
    Portail
    0.59
     internetowa
    0.59
     Divide
    0.57
     divided
    0.56
    aronder
    0.56
    retes
    0.56
    Activations Density 0.103%

    No Known Activations