© 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. 1-CLT-HP
    7. 13757
    Prev
    Next
    INDEX
    Explanations

    walls

    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
    walls
    -0.66
    wall
    -0.58
    ChromeDriver
    -0.53
    UrlResolution
    -0.53
    نگار
    -0.52
     walls
    -0.51
    RegistryLite
    -0.51
    rafat
    -0.49
     Wallflower
    -0.48
    Personendaten
    -0.48
    POSITIVE LOGITS
     ujednoznacz
    0.63
    deja
    0.52
     incontra
    0.51
     hommes
    0.48
     récomp
    0.48
     Worse
    0.47
     vreme
    0.47
     remedio
    0.46
    Недостатки
    0.46
     vecteur
    0.46
    Activations Density 0.040%

    No Known Activations