© 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. 6-RES-MATRYOSHKA-DC
    7. 884
    Prev
    Next
    INDEX
    Explanations

    abstract concepts of ability and the capacity to do something

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consider
    -0.69
    utnik
    -0.65
     involve
    -0.60
    amom
    -0.60
    vieja
    -0.59
     contemplate
    -0.57
     involving
    -0.56
     contemplated
    -0.56
    ন
    -0.55
    openConnection
    -0.54
    POSITIVE LOGITS
     ability
    1.60
     Ability
    1.56
    Ability
    1.46
     abilities
    1.45
     Abilities
    1.41
     inability
    1.38
     capability
    1.36
     able
    1.33
     Able
    1.30
    Able
    1.27
    Activations Density 0.501%

    No Known Activations