© 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. 30
    Prev
    Next
    INDEX
    Explanations

    complex sentences with multiple clauses and negative connotations.

    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
     négociations
    -1.00
     hâte
    -0.96
     boî
    -0.93
     larmes
    -0.92
     étoient
    -0.89
     découver
    -0.86
     plufieurs
    -0.86
     épaules
    -0.84
     lèvres
    -0.82
     avoient
    -0.82
    POSITIVE LOGITS
     moral
    0.94
     human
    0.90
     society
    0.79
     humanity
    0.78
     self
    0.77
     political
    0.76
     societal
    0.76
     fundamental
    0.73
     morality
    0.73
     universal
    0.73
    Activations Density 12.352%

    No Known Activations