© 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. 24
    Prev
    Next
    INDEX
    Explanations

    various seemingly arbitrary character sequences, including strings of hyphens and dollar signs, numerical IDs with colons, and hexadecimal color codes.

    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
    Бахар
    -0.88
    下载附件
    -0.85
     للاسماء
    -0.84
     CanadaChoose
    -0.81
    Jeografia
    -0.73
     مُعرِّف
    -0.73
    исленность
    -0.70
    帖最后由
    -0.68
     الرياضيه
    -0.65
     szóci
    -0.65
    POSITIVE LOGITS
    0
    1.24
    1
    1.16
    4
    1.15
    2
    1.15
    3
    1.07
    5
    1.03
    8
    0.96
    9
    0.94
    7
    0.91
    6
    0.86
    Activations Density 8.509%

    No Known Activations