© 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. 2341
    Prev
    Next
    INDEX
    Explanations

    the first-person perspective, particularly the speaker explaining what they mean

    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
    fromnode
    -0.60
    PerformLayout
    -0.59
    endphp
    -0.53
    styleable
    -0.44
    Istorija
    -0.43
    しが
    -0.42
    qtype
    -0.41
    ftagPool
    -0.41
    terne
    -0.41
    RenderAtEndOf
    -0.41
    POSITIVE LOGITS
     means
    3.09
     meaning
    3.08
     mean
    3.05
     MEAN
    2.84
    means
    2.80
     Meaning
    2.66
     Means
    2.66
    meaning
    2.64
    Meaning
    2.63
     meant
    2.61
    Activations Density 0.782%

    No Known Activations