© 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. 12-RES-MATRYOSHKA-DC
    7. 2081
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-sabotage and the impact of personal choices on happiness and success

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     Meksiku
    -0.63
    DataSnapshot
    -0.59
    +:+
    -0.59
     nationwide
    -0.53
    AndroidJUnit
    -0.52
     Nunn
    -0.52
    InitVars
    -0.51
    idis
    -0.50
     Cowan
    -0.50
    ΩΝ
    -0.50
    POSITIVE LOGITS
    RectangleBorder
    0.63
     tibet
    0.57
    icestershire
    0.54
     yourself
    0.53
     houſe
    0.52
     ModelExpression
    0.52
    yourself
    0.52
     BPS
    0.51
    amazonaws
    0.51
    autique
    0.51
    Activations Density 0.551%

    No Known Activations