© 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. 2151
    Prev
    Next
    INDEX
    Explanations

    references to specific guidelines or standards for evaluation

    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
    hülle
    -0.65
    𝘨
    -0.65
    shapes
    -0.64
    expandindo
    -0.63
     Shand
    -0.62
    deth
    -0.61
    Topology
    -0.60
    welle
    -0.60
     آس
    -0.60
    ASS
    -0.60
    POSITIVE LOGITS
     Criteria
    1.43
     criteria
    1.42
    criteria
    1.40
     CRITERIA
    1.39
    Criteria
    1.34
    ITERIA
    1.13
     Criterion
    1.09
    riteria
    1.05
     criterion
    1.00
     criterio
    0.95
    Activations Density 0.007%

    No Known Activations