© 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. 5-CLT-HP
    7. 92592
    Prev
    Next
    INDEX
    Explanations

    was

    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
    rungsseite
    -0.72
     متعلقه
    -0.65
     GenerationType
    -0.64
     propOrder
    -0.63
     tonight
    -0.60
    wpi
    -0.60
    eload
    -0.59
     kasarigan
    -0.59
    たまたま
    -0.58
    adpleegd
    -0.57
    POSITIVE LOGITS
    istoitu
    0.50
     vork
    0.45
     écart
    0.44
     particularly
    0.43
    __*/
    0.43
     destinées
    0.42
    blockList
    0.42
    Các
    0.42
    demás
    0.42
     heer
    0.41
    Activations Density 0.010%

    No Known Activations