© 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. 24-RES-MATRYOSHKA-DC
    7. 570
    Prev
    Next
    INDEX
    Explanations

    genetics

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     betweenstory
    -0.64
     relâche
    -0.58
    apimachinery
    -0.45
    ిక
    -0.44
    ائح
    -0.42
     onPage
    -0.42
    Enllaços
    -0.41
    jmp
    -0.41
    Serializable
    -0.41
    навли
    -0.39
    POSITIVE LOGITS
     condition
    1.28
     state
    1.26
     상태
    1.19
    状态
    1.13
     condizione
    1.13
    condition
    1.11
    状態
    1.11
     Zustand
    1.11
     status
    1.09
    state
    1.08
    Activations Density 3.015%

    No Known Activations