© 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. 1-CLT-HP
    7. 13153
    Prev
    Next
    INDEX
    Explanations

    leaves

    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
     TestBed
    -0.61
     LUMP
    -0.53
    dotte
    -0.49
    Élet
    -0.49
    щет
    -0.48
    aino
    -0.46
     membagikan
    -0.46
    toEqual
    -0.46
     desaparecido
    -0.45
    oise
    -0.44
    POSITIVE LOGITS
     SwitchCompat
    0.66
     myſelf
    0.64
     olives
    0.62
    PerformLayout
    0.61
     Sardin
    0.61
     amphibians
    0.60
    hitheatre
    0.59
     Monfieur
    0.59
     daggers
    0.59
    PMailer
    0.58
    Activations Density 0.038%

    No Known Activations