© 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. 864
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "such a" or "such," indicating examples or emphasis

    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
    IDO
    -0.77
     Cleo
    -0.77
    FloatField
    -0.69
    ido
    -0.68
    en
    -0.66
     Catto
    -0.66
    emo
    -0.64
    IntegerField
    -0.64
    platte
    -0.64
     McNamara
    -0.63
    POSITIVE LOGITS
     SUCH
    1.18
    such
    1.15
     such
    1.13
    Such
    1.13
     Such
    1.07
     suche
    1.02
     Roskov
    0.92
     Infórmanos
    0.90
    uch
    0.89
     nahilalakip
    0.86
    Activations Density 0.376%

    No Known Activations