© 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. 797
    Prev
    Next
    INDEX
    Explanations

    instances of "you" or "we" alongside auxiliary verbs such as "will", "should", "has", "have", and "are"

    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
    Siehe
    -0.52
    Dislikes
    -0.50
    gestone
    -0.49
    cticut
    -0.46
    Personendaten
    -0.44
    Didn
    -0.44
     आप
    -0.43
    Wasn
    -0.42
    congrats
    -0.42
    Believe
    -0.41
    POSITIVE LOGITS
     need
    2.53
     must
    2.20
     needs
    2.13
    need
    2.02
     should
    2.00
     Need
    1.84
    must
    1.84
    needs
    1.80
     harus
    1.75
    Need
    1.75
    Activations Density 1.822%

    No Known Activations