© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14318
    Prev
    Next
    INDEX
    Explanations

    instances of the word "positive" or variations related to positivity

    oai_token-act-pair · gpt-4.1-nano
    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
    WebMethod
    -0.63
    KURZBESCHREIBUNG
    -0.62
     CURIAM
    -0.60
    AutoScaleMode
    -0.59
    __':
    -0.58
     cease
    -0.52
    /**
    -0.52
     متعلقه
    -0.50
    )__
    -0.49
    __":
    -0.49
    POSITIVE LOGITS
    itive
    3.84
    itively
    2.42
    itives
    1.84
    ITIVE
    1.27
    itiv
    1.25
    ition
    1.09
    itivo
    1.08
    itiva
    1.05
    nitive
    0.92
    itif
    0.83
    Activations Density 0.001%

    No Known Activations