© 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. 0-CLT-HP
    7. 93987
    Prev
    Next
    INDEX
    Explanations

    foster

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foster
    -2.17
    foster
    -1.88
     FOSTER
    -1.69
    Foster
    -1.59
     Foster
    -1.59
     fostering
    -1.51
     fosters
    -1.51
     fostered
    -1.45
     Fost
    -1.21
     adoptive
    -0.77
    POSITIVE LOGITS
    able
    0.92
    ings
    0.84
    ingly
    0.82
    iness
    0.66
    age
    0.65
    adays
    0.64
    ments
    0.63
    ability
    0.63
    oirs
    0.58
    ishments
    0.57
    Activations Density 0.207%

    No Known Activations