© 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. 20162
    Prev
    Next
    INDEX
    Explanations

    elements associated with strong emotional experiences and personal reflection

    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
    #
    -0.66
    stdc
    -0.64
    UserScript
    -0.63
    bestos
    -0.52
     quarries
    -0.51
     zirc
    -0.51
    évaluateur
    -0.50
     Fath
    -0.48
     tiên
    -0.48
     sequins
    -0.48
    POSITIVE LOGITS
    Personensuche
    0.69
    HasAnnotation
    0.60
    DebuggerStep
    0.59
     вікі
    0.56
    EndInit
    0.54
    Traceback
    0.54
     it
    0.51
    rounding
    0.51
    espero
    0.51
    rensa
    0.50
    Activations Density 0.192%

    No Known Activations