© 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. 18-RES-MATRYOSHKA-DC
    7. 93
    Prev
    Next
    INDEX
    Explanations

    sentences that are providing context or a transition between ideas

    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.18.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.18.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
     Majefty
    -0.99
     Shakspeare
    -0.98
    tvguidetime
    -0.97
     betweenstory
    -0.95
     Cæsar
    -0.93
     Efq
    -0.86
     Houſe
    -0.86
    antaranya
    -0.84
     '\\;'
    -0.82
     myſelf
    -0.82
    POSITIVE LOGITS
     there
    1.48
     it
    1.47
     the
    1.41
     we
    1.24
     if
    1.05
     although
    1.04
     they
    1.01
     this
    1.00
     when
    0.96
     many
    0.93
    Activations Density 4.406%

    No Known Activations