© 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. 95004
    Prev
    Next
    INDEX
    Explanations

    emails and forums

    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
    Geplaatst
    -0.83
    LookAnd
    -0.81
    TestingModule
    -0.74
    DockStyle
    -0.74
    urlpatterns
    -0.71
    parsedMessage
    -0.67
    ,’”
    -0.66
    enderror
    -0.66
    PrototypeOf
    -0.65
     metallurgical
    -0.64
    POSITIVE LOGITS
     -
    0.57
     guys
    0.50
     here
    0.50
     OnTriggerEnter
    0.49
     bandes
    0.47
     Here
    0.46
     Dave
    0.45
    Източници
    0.45
    :
    0.45
     it
    0.45
    Activations Density 0.008%

    No Known Activations