© 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. 19898
    Prev
    Next
    INDEX
    Explanations

    discussions about denial and avoidance of responsibility

    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
     مرئيه
    -0.68
    JsonProperty
    -0.59
    Erreferentziak
    -0.55
    strategia
    -0.55
     verdade
    -0.52
    theore
    -0.52
    cterms
    -0.48
    conium
    -0.48
    SerializedName
    -0.47
     Poly
    -0.47
    POSITIVE LOGITS
    Lähteet
    0.68
    UserScript
    0.65
    :+:
    0.60
    ✨:
    0.59
     nahilalakip
    0.56
    IUrlHelper
    0.56
     yüzden
    0.52
     незавершена
    0.52
    ⓘ
    0.51
    namespace
    0.50
    Activations Density 0.159%

    No Known Activations