© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1087
    Prev
    Next
    INDEX
    Explanations

    to

    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
     excision
    -0.61
    ItemBackground
    -0.60
     bättre
    -0.59
    RegistryLite
    -0.57
    NameInMap
    -0.57
     CreateTagHelper
    -0.57
    gonic
    -0.56
    JOptionPane
    -0.54
     stalker
    -0.54
    Gön
    -0.53
    POSITIVE LOGITS
    Rüyada
    0.63
    InputTagHelper
    0.56
    welling
    0.51
    Portale
    0.47
    FIX
    0.46
    pples
    0.46
     get
    0.45
    #+#
    0.43
    Kaieteur
    0.43
    pple
    0.43
    Activations Density 0.001%

    No Known Activations