© 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. 5-CLT-HP
    7. 97712
    Prev
    Next
    INDEX
    Explanations

    likes

    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
     }^{[
    -0.49
     broadening
    -0.49
     sabbia
    -0.47
     étoient
    -0.45
     assise
    -0.45
     Spéc
    -0.45
     acrylique
    -0.45
     første
    -0.44
     selecting
    -0.44
     tredje
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.87
    httphttps
    0.84
    Geplaatst
    0.73
    BeginContext
    0.73
     kasarigan
    0.71
    __*/
    0.70
     Normdatei
    0.67
    TagMode
    0.66
    ArrowToggle
    0.66
    RegistryLite
    0.65
    Activations Density 0.001%

    No Known Activations