© 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. 22-RES-MATRYOSHKA-DC
    7. 2450
    Prev
    Next
    INDEX
    Explanations

    topics involving an outside, unknown party accessing one's personal information or space, or topics related to playing American football.

    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.22.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.22.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
    شهاد
    -0.87
    φαλ
    -0.57
    extAlignment
    -0.55
    geslacht
    -0.51
    stdc
    -0.51
    결
    -0.50
    ammans
    -0.49
    SceneManagement
    -0.49
    ########.
    -0.49
    LookAnd
    -0.48
    POSITIVE LOGITS
     intrusion
    1.52
     intrusions
    1.36
     invade
    1.28
     intru
    1.27
     intr
    1.27
     intrusive
    1.27
     invading
    1.24
     encro
    1.20
     Intru
    1.20
     invasion
    1.19
    Activations Density 1.068%

    No Known Activations