© 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. 0-CLT-HP
    7. 983
    Prev
    Next
    INDEX
    Explanations

    Remaining, damaged, survivors

    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
     kasarigan
    -0.81
     ModelExpression
    -0.79
     varandra
    -0.75
     fallait
    -0.68
     énergé
    -0.68
     preghiera
    -0.67
     مرئيه
    -0.65
     céramique
    -0.65
     سكانية
    -0.64
     élevées
    -0.64
    POSITIVE LOGITS
    ness
    0.59
     chỗ
    0.57
    lied
    0.56
    nitive
    0.51
     dose
    0.50
     norm
    0.50
    brev
    0.50
     Bonne
    0.49
     exp
    0.49
     Bew
    0.49
    Activations Density 0.042%

    No Known Activations