© 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. 45613
    Prev
    Next
    INDEX
    Explanations

    random text

    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
     nakalista
    -0.47
     rev
    -0.42
    saraba
    -0.41
     hab
    -0.40
    Ordre
    -0.40
     real
    -0.40
     syn
    -0.39
    onViewCreated
    -0.39
     bru
    -0.39
    databind
    -0.39
    POSITIVE LOGITS
     poffe
    0.82
     purpoſe
    0.79
    DeleteBehavior
    0.77
     occaf
    0.77
     raiſ
    0.75
    expandindo
    0.73
    AndEndTag
    0.72
     paſſ
    0.72
     esternos
    0.71
     femininas
    0.71
    Activations Density 0.006%

    No Known Activations