© 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. 20-CLT-HP
    7. 72367
    Prev
    Next
    INDEX
    Explanations

    Chemistry and random strings

    np_max-act-logits · 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
    
    -0.61
    tvguidetime
    -0.58
    ynb
    -0.57
    slidesPer
    -0.54
     incomplete
    -0.54
    PoolSize
    -0.53
    setBold
    -0.52
     indietro
    -0.52
     Baillargeon
    -0.52
     headlights
    -0.51
    POSITIVE LOGITS
     mxArray
    0.57
    లాలు
    0.51
    Manbalar
    0.47
    arm
    0.47
    CreateMap
    0.47
    orm
    0.47
    siven
    0.43
    temming
    0.42
    asilkan
    0.41
     im
    0.40
    Activations Density 0.000%

    No Known Activations