© 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. 28480
    Prev
    Next
    INDEX
    Explanations

    instances of self-reference and strong emotional expressions

    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
     Efq
    -0.82
     Chrift
    -0.71
     Chriftian
    -0.70
     ſtate
    -0.68
    +#+
    -0.67
     themſelves
    -0.67
    databind
    -0.66
     Jefus
    -0.65
    KURZBESCHREIBUNG
    -0.65
     purpoſe
    -0.64
    POSITIVE LOGITS
    ativement
    0.68
    BeginContext
    0.58
    awtextra
    0.54
    Przypisy
    0.51
    中には
    0.48
    際は
    0.48
    sep
    0.48
     pou
    0.47
    tvguidetime
    0.47
    yntaxException
    0.46
    Activations Density 0.000%

    No Known Activations