© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4397
    Prev
    Next
    INDEX
    Explanations

    terms related to barriers and constraints within systems or processes

    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
    thâu
    -0.48
    Uninitialized
    -0.47
    Oise
    -0.47
     szabad
    -0.44
     Betracht
    -0.44
     ErrInvalid
    -0.42
     whither
    -0.41
     casual
    -0.41
    casual
    -0.40
     unsteady
    -0.40
    POSITIVE LOGITS
     impenetrable
    0.87
     blocking
    0.82
     tight
    0.81
     barriers
    0.81
     locked
    0.80
     blockage
    0.78
    Barriers
    0.76
     Restrictions
    0.76
     restricting
    0.76
     Tight
    0.75
    Activations Density 0.668%

    No Known Activations